Path
TRADING4AI / Reliability / Public Materials / Counterparty screening before payment
Public Material Pack
A financial agent is about to prepare a cross-border vendor payment or wallet transfer to a new counterparty with incomplete verification.
Boundary
Pages-only static material in this phase.
No backend judgment, no backtesting, no Tencent runtime, and no user-submitted verification queue.
This pack is public review guidance, not compliance clearance or final approval.
Path
TRADING4AI / Reliability / Public Materials / Counterparty screening before payment
On this page
Plain-language summary
Use this static pack before a financial agent accepts a counterparty, beneficiary, invoice, wallet, or settlement instruction as safe enough for payment.
Example input
A user asks whether an overseas vendor, beneficiary, or wallet destination is safe enough to pay based on partial identity and payment evidence.
Expected static output
A source-bound action note that separates counterparty identity, payment details, screening sources, match confidence, missing inputs, and unresolved escalation triggers.
Best used when
Not used for
Source freshness
This pack preserves a static source snapshot and citation trail; it does not fetch fresh third-party data at request time.
Agent reading hint
Read the HTML page first for boundaries, then use the JSON artifact for structured retrieval.
Why this pack exists
This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Linked service: Action Preflight
Pack id: counterparty_screening_pack
What this is not
Not a live review queue.
Not a request-time API.
Not a buy/sell/execute system.
Not a legal, sanctions, or compliance verdict.
Inputs / outputs
Each pack stays readable for both humans and crawlers by using the same stable, bounded sections.
Inputs
Outputs
How to use this pack
This page explains a single review scenario. Use it to understand what evidence the scenario needs, what a bounded output looks like, and when the reader should stop, escalate, or move to a linked artifact.
Use this pack when
Stop at this pack when
Move to the linked artifact when
Pack JSON artifact: /reliability/public-materials/counterparty-screening-pack.json
Linked service page: Action Preflight
This pack does not do
Usage fit
Suitable for
Not suitable for
Source / limitation policy
Delivery shape
These sections make the pack more than a scenario description. They define the minimum evidence set, the bounded outputs the review should return, and the citation rules that keep the result trustworthy.
Evidence to collect
Delivery outputs
Decision matrix
Status: unresolved
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record the OFAC Sanctions List Service query basis, exact name or alias searched, source URL, retrieval time, and whether the result is exact, partial, no-hit, or unresolved.
Allowed static use: Use only as a source-bound evidence row describing the OFAC match state and unresolved identifiers in this static pack.
Blocked upgrade: Do not convert an OFAC no-hit or partial search into sanctions clearance, safe counterparty approval, compliant payment approval, or permission to proceed.
Agent action: Record the match state, hold payment review, and escalate when the name, alias, jurisdiction, or identifier remains unresolved.
Status: unresolved
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record the Trade.gov Consolidated Screening List source, query terms, source categories checked, retrieval time, and exact/partial/no-hit semantics.
Allowed static use: Use as static evidence that the CSL source is required and that source semantics must be preserved before any payment summary.
Blocked upgrade: Do not say the counterparty is verified, safe, approved, compliant, or cleared to proceed because a static CSL row exists.
Agent action: Record the CSL evidence state and escalate if source category, query term, or match confidence is missing.
Status: unresolved
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record SAM.gov or GSA Exclusions API source context, entity identifiers, exclusion-source timestamp, and whether identifiers are complete enough to interpret the row.
Allowed static use: Use as an evidence requirement row for exclusion review and unresolved identifier handling.
Blocked upgrade: Do not treat an incomplete exclusion query as safe, compliant, approved, verified, or cleared for payment approval.
Agent action: Hold review and record missing identifiers when the exclusion row cannot be reconciled to the named counterparty.
Status: unresolved
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record World Bank debarred-firms source URL, name and jurisdiction searched, procurement relevance, retrieval time, and match semantics.
Allowed static use: Use as source-bound evidence for procurement-style screening context and unresolved match handling.
Blocked upgrade: Do not convert a no-hit, missing query, or static source mention into compliant vendor approval or safe payment clearance.
Agent action: Record the procurement-source status and escalate when the counterparty, jurisdiction, or beneficiary match remains unresolved.
Status: unresolved
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record CFTC RED List relevance when the counterparty offers trading, investment, brokerage-like, or signal-service activity.
Allowed static use: Use as static evidence that trading-services counterparties need public-warning review before payment trust is upgraded.
Blocked upgrade: Do not treat absence of a RED List row as verified, safe, approved, compliant, or permission to proceed with payment.
Agent action: Escalate trading-service counterparties when RED List relevance, source query, or match confidence is missing.
Status: warning
Evidence fields: operator_identity, source_links, match_confidence
Source requirement: Record OpenSanctions only as aggregator context for aliases, identifiers, and entity-resolution hints, while preserving official-source citation separately.
Allowed static use: Use aggregator evidence to explain alias and match uncertainty, not as the final source of clearance.
Blocked upgrade: Do not upgrade aggregator context into official clearance, safe counterparty approval, compliant payment approval, or verified beneficial ownership.
Agent action: Record aggregator context, cite official sources separately, and escalate when official-source evidence is missing.
Citation rules
Static sample deliverable
These sample fields make the pack feel closer to a real deliverable: a sample input summary, concrete evidence records, and a bounded output that stays inside static-review limits.
Sample input summary
Draft payment request: a cross-border supplier payment adds a new beneficiary and arrives from an unverified finance email shortly before settlement.
Sample evidence records
Status: warning
Source: Previously verified vendor record (sample)
Retrieved: 2026-05-25T00:00:00.000Z
The draft names Blue Harbor Asia Services, while the stored payee record remains Blue Harbor Consulting Ltd.
Status: confirmed
Source: OFAC Sanctions List Service
Retrieved: 2026-05-25T00:00:00.000Z
No exact hit is not a safety clearance and does not verify beneficial ownership.
Status: unresolved
Source: Counterparty screening entity-resolution checklist
Retrieved: 2026-05-25T00:00:00.000Z
The sample has a beneficiary name and payment destination, but lacks stable identifiers, alias handling, country context, and source-by-source partial-match or no-hit notes.
Status: unresolved
Source: Trade.gov Consolidated Screening List
Retrieved: 2026-05-25T00:00:00.000Z
This static pack names the CSL as a required authoritative source, but it does not perform a live query or issue clearance.
Status: unresolved
Source: SAM.gov Exclusions API
Retrieved: 2026-05-25T00:00:00.000Z
A payment reviewer should record whether the counterparty was checked against exclusions; this sample does not claim a no-hit result.
Status: unresolved
Source: World Bank debarred firms
Retrieved: 2026-05-25T00:00:00.000Z
The World Bank source is cited as a public debarment reference; this pack does not replace a current sanctions or procurement compliance check.
Status: unresolved
Source: CFTC RED List
Retrieved: 2026-05-25T00:00:00.000Z
The RED List is relevant to trading-related counterparties; absence of a cited result here is not approval to proceed.
Status: warning
Source: OpenSanctions public reference
Retrieved: 2026-05-25T00:00:00.000Z
OpenSanctions may help normalize aliases and identifiers, but this pack must still cite official sources separately and must not treat aggregator output as compliance clearance.
Status: warning
Source: FTC cryptocurrency scam guidance
Retrieved: 2026-05-25T00:00:00.000Z
The FTC source is public warning context for crypto payment pressure; it does not verify the counterparty or approve settlement.
Status: warning
Source: Verified supplier portal record (sample)
Retrieved: 2026-05-25T00:00:00.000Z
The bank-detail change was sent from a new domain and was not confirmed in the known supplier portal.
Status: unresolved
Source: Supplier onboarding packet (sample)
Retrieved: 2026-05-25T00:00:00.000Z
The current request relies on forwarded payment instructions only.
Evidence Card sample
Counterparty screening before payment sample evidence card
Review verdict: review
Checked selected public sources and sample records at the retrieval time shown; the evidence remains incomplete across alias, identifier, jurisdiction, and no-hit semantics, so the payment stays in review, is not cleared, and is not approved by this pack.
Citation block
Key findings
Required disclosures
Do not claim
Action routing
actionRouting type: counterparty_payment_review
Preflight stage: before_payment_or_contracting
Default posture: review
Primary action risk: Counterparty identity, public-warning checks, sanctions/list screening, and payment-beneficiary evidence may be incomplete before money moves.
Minimum input field ids: operator_identity, payment_destination, source_links, match_confidence
Minimum required inputs
Missing input fallback
Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
Route when
Stop or escalate when
Search intent
Intent id: counterparty_screening_pack_search_intent
User task: Screen a vendor, customer, wallet owner, or payment counterparty before a transfer or wire.
Route reason: Route to Counterparty screening before payment when the user task matches counterparty_payment_review and needs A source-bound action note that separates counterparty identity, payment details, screening sources, match confidence, missing inputs, and unresolved escalation triggers.
queryExamples: verify vendor before wire, screen counterparty before payment, counterparty screening evidence, OFAC vendor screening before payment, supplier wire transfer evidence card, check company before paying invoice
Use when
Do not use as
Escalate to qualified human review when required inputs are missing, source confidence is unresolved, payment or transfer risk is present, or the user asks for approval, clearance, execution, suitability, or compliance guarantees.
Input field glossary
operator_identity: The seller, operator, issuer, vendor, or organization identity behind the request. Missing input risk: The agent may route money or trust claims to an unverified or impersonated operator.
payment_destination: The bank account, wallet address, checkout link, invoice beneficiary, or settlement rail that would receive funds. Missing input risk: The agent cannot compare the destination against the named counterparty or prior approved instructions.
source_links: Official registries, warning pages, filings, releases, or cited public pages used as evidence. Missing input risk: The agent cannot separate source-bound evidence from unsourced assertion.
match_confidence: How exact, partial, alias-based, or unresolved a source match is against the named counterparty. Missing input risk: The agent may either block a legitimate action or miss a serious warning signal.
Preflight questionnaire
Answer every question with source-bound evidence before upgrading the review posture; if any required input is missing, apply the missing-input fallback and do not treat the static pack as approval.
operator_identity: What evidence identifies the operator identity for this counterparty_payment_review review? Acceptable evidence: legal name, known aliases, website, registration number, public profile. If missing: The agent may route money or trust claims to an unverified or impersonated operator. Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
payment_destination: What evidence identifies the payment destination for this counterparty_payment_review review? Acceptable evidence: bank account, wallet address, subscription checkout URL, invoice beneficiary. If missing: The agent cannot compare the destination against the named counterparty or prior approved instructions. Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
source_links: What evidence identifies the source links for this counterparty_payment_review review? Acceptable evidence: OFAC URL, SEC filing URL, FRED series URL, public warning page. If missing: The agent cannot separate source-bound evidence from unsourced assertion. Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
match_confidence: What evidence identifies the match confidence for this counterparty_payment_review review? Acceptable evidence: exact legal-name match, alias match, jurisdiction mismatch, unresolved partial match. If missing: The agent may either block a legitimate action or miss a serious warning signal. Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
Decision policy
Default posture: review
Allowed static output: Checked selected public sources and sample records at the retrieval time shown; the evidence remains incomplete across alias, identifier, jurisdiction, and no-hit semantics, so the payment stays in review, is not cleared, and is not approved by this pack.
Blocked static output: This counterparty is safe and the payment can proceed.
Proceed only when
Fallback when missing inputs
Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved.
Stop or escalate when
Escalate to human review when any stop-or-escalate rule applies, when required evidence is missing, or when the requested action would treat this static pack as approval, clearance, execution advice, or live screening.
Decision guardrails
escalate: One or more minimum inputs are missing or uncited: Counterparty legal name, aliases, jurisdiction, website, registration number, or public profile evidence.; Payment beneficiary details, bank account, wallet address, invoice, contract, or settlement instruction to compare.; Source links used for sanctions, exclusions, debarment, RED List, warning, or public registry review.; Match confidence notes that separate exact matches, aliases, partial matches, and unresolved identifiers.. Required action: Defer payment or onboarding; collect missing identifiers and source links, then escalate if match confidence or beneficiary ownership remains unresolved. Allowed output: Checked selected public sources and sample records at the retrieval time shown; the evidence remains incomplete across alias, identifier, jurisdiction, and no-hit semantics, so the payment stays in review, is not cleared, and is not approved by this pack. Blocked upgrade: This counterparty is safe and the payment can proceed. Human review required: yes.
escalate: Any stop-or-escalate trigger applies: Exact identity, jurisdiction, beneficiary ownership, or source match confidence is unresolved.; A sanctions, exclusion, debarment, RED List, public-warning, or adverse public-source signal appears.; Payment instructions changed in a private chat, forwarded message, or new email domain.; The beneficiary or wallet is new and cannot be independently matched to the claimed counterparty.; The request relies on urgency, secrecy, guaranteed safety, or informal exceptions to normal review.. Required action: Stop automatic action, keep the unresolved risk visible, and route the item to human review before payment, publication, execution, or downstream trust transfer. Allowed output: Checked selected public sources at the stated retrieval time; no clearance decision was established by this pack alone. The current evidence is incomplete, so the payment should stay in review rather than move forward automatically. This pack can describe what was checked and what remains unresolved, but it does not certify the counterparty. Blocked upgrade: This counterparty is safe. This payment is compliant and can proceed. No further review is needed because no risk was found in the public sources checked. Human review required: yes.
allow_with_limits: All minimum inputs are collected, cited, and no stop-or-escalate trigger applies; the output still remains a bounded static material summary. Required action: Emit only source-bound, timestamped, limitation-preserving static output and carry unresolved items into the final note. Allowed output: Checked selected public sources and sample records at the retrieval time shown; the evidence remains incomplete across alias, identifier, jurisdiction, and no-hit semantics, so the payment stays in review, is not cleared, and is not approved by this pack. Blocked upgrade: This counterparty is safe and the payment can proceed. Human review required: no.
Misuse patterns
block: No-hit treated as clearance. False signal: An official source search returns no exact hit, so the agent says the counterparty is cleared. Why misleading: A no-hit can reflect incomplete identifiers, aliases, jurisdiction gaps, stale source timing, or a source that does not cover the relevant risk. Safe alternative: State the source, query basis, retrieval time, and no-hit limitation; keep payment under review until identity and beneficiary evidence are reconciled. Blocked agent action: Do not approve payment, call the counterparty safe, or claim sanctions/compliance clearance from a no-hit row. Evidence fields: operator_identity, source_links, match_confidence.
escalate: Aggregator context treated as official clearance. False signal: OpenSanctions or another aggregator has context, so the agent treats it as official screening clearance. Why misleading: Aggregator context can help entity resolution, but official sources still need separate citation, query terms, retrieval time, and match semantics. Safe alternative: Use aggregator output only for alias or identifier context, then cite official registry rows separately and keep unresolved matches visible. Blocked agent action: Do not replace official-source screening with aggregator context or call the payment compliant, approved, verified, or safe. Evidence fields: operator_identity, source_links, match_confidence.
escalate: Beneficiary or wallet destination collapsed into counterparty identity. False signal: The invoice, bank account, wallet, or payment destination is present, so the agent treats it as proof of counterparty ownership. Why misleading: Payment destination data is not the same as legal identity, beneficial ownership, official domain control, or verified payment-channel authority. Safe alternative: Separate counterparty identity from payment destination evidence and require a signed, portal, prior-channel, or official-domain link before proceeding. Blocked agent action: Do not approve transfer, payment, onboarding, or wallet trust when beneficiary ownership or payment-channel authority is unresolved. Evidence fields: operator_identity, payment_destination, match_confidence.
Static action note template
Use only as a static, source-bound Action Preflight note after completing action routing, the preflight questionnaire, and the decision policy.
This is a static action note template, not approval, not live screening, not backtesting, not execution advice, and not a clearance decision.
Required sections
Static action note example
Example id: counterparty_screening_pack_static_action_note_example
Note status: review
Source snapshot: 2026-05-25T00:00:00.000Z
This is a static action note template, not approval, not live screening, not backtesting, not execution advice, and not a clearance decision.
Filled sections
Agent workflow
Workflow id: counterparty_screening_pack_agent_workflow
Step ids: select_pack, collect_minimum_inputs, answer_preflight_questionnaire, apply_decision_policy, draft_static_action_note, cite_and_escalate
Linked example: counterparty_screening_pack_static_action_note_example
Canonical citation: Counterparty screening before payment, public-material-counterparty-screening-pack-2026-05-25, generated 2026-05-25T00:00:00.000Z, source snapshot 2026-05-25T00:00:00.000Z, https://trading4ai.com/agent-verification/materials/counterparty-screening-pack
Escalate to qualified human review when required inputs are missing, source confidence is unresolved, payment or transfer risk is present, or the user asks for approval, clearance, execution, suitability, or compliance guarantees.
Source quality
sourceQuality pack id: counterparty_screening_pack
Action type: counterparty_payment_review
Workflow id: counterparty_screening_pack_agent_workflow
Source kinds: official_guidance, official_registry, public_reference, sample_page
Source manifest count: 8
Official registry sources: 5
Official guidance sources: 1
Source quality profile: registry_heavy
Registry coverage expectation: primary_for_this_static_pack
This pack is registry-heavy because counterparty screening depends on source-bound sanctions, exclusions, debarment, and warning-list semantics before a payment can be discussed safely.
Agent source use
Sample evidence records: 11
Source snapshot: 2026-05-25T00:00:00.000Z
Boundary: static_source_manifest_not_live_screening
Source review policy
sourceReviewPolicy.nextRecommendedReviewAt: 2026-06-24T00:00:00.000Z
Review cadence: 30 days
Review mode: manual_public_source_recheck_required
Catalog field: sourceReviewPolicyIndex
This is a static source-review policy for a pre-generated public material pack; it is not live screening, request-time judgment, compliance clearance, payment approval, or trading advice.
Refresh triggers (sourceReviewPolicy.refreshRequiredWhen)
Case readiness checklist
caseReadinessChecklist: counterparty_screening_pack_case_readiness_checklist
sourceFreshnessGate: Before reuse, compare the case date and cited source retrieval plan with sourceReviewPolicy.nextRecommendedReviewAt=2026-06-24T00:00:00.000Z; if the static snapshot is stale, re-check sources and version the artifact before using it.
Default posture: review
Must confirm before use
Not ready signals
Ready static handoff
Case worksheet
caseWorksheet: counterparty_screening_pack_case_worksheet
worksheetType: counterparty_source_query_ledger
Treat this worksheet as complete only when every row preserves source/citation fields, result semantics, safe rewrite, blocked rewrite, and escalation reason.
OFAC source-query row · OFAC Sanctions List Service
Capture the legal name, aliases, identifiers, jurisdiction, query terms, beneficiary or payment destination, retrieval time, and ownership evidence used for the OFAC source query.
Result semantics: Record exact match, partial match, no-hit, unresolved identifier, alias mismatch, jurisdiction mismatch, and match confidence separately.
Unsafe category: sanctions no-hit upgraded into counterparty clearance or payment approval
Safe restatement: the cited OFAC source row records the query basis and match semantics only; it does not approve the counterparty or payment destination.
Do not say the counterparty is safe, compliant, verified, cleared, approved, or that payment can proceed because this row exists.
Trade.gov CSL source-query row · Trade.gov Consolidated Screening List
Capture CSL query terms, legal name, aliases, source categories, country or jurisdiction, source URL, retrieval time, and payment-destination relationship.
Result semantics: Record exact match, partial match, no-hit, unresolved source category, and match confidence without turning no-hit into clearance.
Unsafe category: CSL no-hit upgraded into compliant vendor approval
Safe restatement: the CSL source row is a source-bound observation with named query terms, retrieval time, and unresolved match limits.
Do not say the vendor is compliant, safe, approved, cleared, verified, or ready to proceed from a static CSL row.
SAM.gov and World Bank query row · SAM.gov Exclusions API / World Bank debarred firms
Capture exclusion/debarment query basis, legal identifiers, jurisdiction, procurement relevance, beneficiary/payment destination, source URL, and retrieval time.
Result semantics: Record exact exclusion or debarment match, partial match, no-hit, unresolved identifier, and match confidence for each source separately.
Unsafe category: exclusion/debarment query treated as complete payment clearance
Safe restatement: these source rows describe exclusion/debarment evidence and unresolved identifiers, not payment approval.
Do not say the counterparty is safe, compliant, verified, approved, cleared, or that payment can proceed because no issue was found.
Trading-services warning and aggregator context row · CFTC RED List / OpenSanctions
Capture trading-service relevance, alias and identifier hints, aggregator context, official-source follow-up, jurisdiction, query basis, match semantics, and retrieval time.
Result semantics: Record exact warning match, partial warning match, no-hit, aggregator-only context, unresolved alias, and source-confidence limits.
Unsafe category: public warning or aggregator context upgraded into official clearance
Safe restatement: warning and aggregator rows can explain risk context and alias uncertainty while official sources remain separate.
Do not say the counterparty is safe, compliant, approved, verified, cleared, or suitable because an aggregator row or no-hit exists.
Beneficiary and payment-destination ownership row · Supplier onboarding packet and verified payment channel sample
Capture beneficiary name, wallet or bank destination, invoice or settlement instruction, known-good channel, domain, ownership proof, and mismatch notes.
Result semantics: Record exact ownership match, partial ownership match, no-hit, unresolved ownership, mismatched beneficiary, or changed destination before any payment handoff.
Unsafe category: beneficiary or wallet ownership gap upgraded into proceed/payment approval
Safe restatement: the beneficiary and destination evidence is incomplete, so the payment remains in review and cannot be approved by the static pack.
Do not say the beneficiary is verified, the wallet is safe, the bank rail is approved, or the payment can proceed.
Source manifest handoff
Sample evidence card id: counterparty_screening_pack_sample_evidence_card
Source manifest entries: 8
Official registry sources: 5
Source quality boundary: static_source_manifest_not_live_screening
Canonical citation artifact version: public-material-counterparty-screening-pack-2026-05-25
Source snapshot: 2026-05-25T00:00:00.000Z
This is a static citation handoff for retrieval. It records cited sources, source roles, evidence links, and limitations without turning the pack into live clearance or approval.
Machine summary
Pack: counterparty_screening_pack
Page: https://trading4ai.com/agent-verification/materials/counterparty-screening-pack
Artifact: https://trading4ai.com/reliability/public-materials/counterparty-screening-pack.json
Action type: counterparty_payment_review
Default posture: review
Minimum input fields: operator_identity, payment_destination, source_links, match_confidence
Decision matrix rows: 6
Evidence verification steps: 5
Misuse patterns: 3
Canonical citation: Counterparty screening before payment, public-material-counterparty-screening-pack-2026-05-25, generated 2026-05-25T00:00:00.000Z, source snapshot 2026-05-25T00:00:00.000Z, https://trading4ai.com/agent-verification/materials/counterparty-screening-pack
Agent use
Do not use as
Decision matrix labels
Evidence verification step labels
Misuse pattern labels
Evidence verification recipe
Pack: counterparty_screening_pack
Default posture: review
Static only: yes
Verification action: Check OFAC, Trade.gov CSL, SAM.gov exclusions, World Bank debarred firms, CFTC RED List, and any listed aggregator context against the exact entity, alias, jurisdiction, and identifier fields in the source manifest.
Trust boundary: A no-hit, partial match, stale query, or aggregator-only row is not sanctions clearance, safe counterparty approval, compliant payment approval, or permission to proceed.
Failure mode: If identifiers, retrieval time, source category, or match confidence are missing, keep the payment in review and do not call the counterparty safe or approved.
Required citation fields: sourceManifest[].url, sourceManifest[].retrievedAt, sourceManifest[].kind, sampleEvidenceRecords[].id, decisionMatrix[].matrixId
Verification action: Match each sample evidence record to a sourceManifest evidenceRecordIds entry, then preserve the record status, note, source label, source URL, and retrievedAt value.
Trust boundary: A sample record explains the static example only; it does not prove the current counterparty, claim, payment, wallet, filing, macro release, or subscription is safe.
Failure mode: If a record cannot be linked to its source manifest row, do not reuse it as evidence and keep the final output unresolved.
Required citation fields: sampleEvidenceRecords[].id, sampleEvidenceRecords[].status, sampleEvidenceRecords[].sourceUrl, sampleEvidenceRecords[].retrievedAt, sourceManifest[].evidenceRecordIds
Verification action: Read all 6 decision matrix rows and carry their allowedStaticUse, blockedUpgrade, and agentAction fields into any downstream summary.
Trust boundary: Decision matrix rows define allowed static reuse and blocked upgrades; they are not automatic live approval, live screening, compliance sign-off, or execution permission.
Failure mode: If a downstream sentence conflicts with a blockedUpgrade row, block or rewrite the sentence and escalate when money, publication, or user action is involved.
Required citation fields: decisionMatrix[].matrixId, decisionMatrix[].status, decisionMatrix[].allowedStaticUse, decisionMatrix[].blockedUpgrade
Verification action: Preserve the canonical citation text, artifact version, generatedAt, staticSnapshotAt, sourceSnapshotAt, and all source retrievedAt values when citing this pack.
Trust boundary: A citation proves the static artifact and source snapshot were recorded; it does not prove the facts are current beyond the listed timestamps.
Failure mode: If artifact version, generatedAt, sourceSnapshotAt, or source retrievedAt values are removed, the output is no longer evidence-bound.
Required citation fields: canonicalCitation.recommendedCitationText, artifactProvenance.artifactVersion, artifactProvenance.generatedAt, canonicalCitation.sourceSnapshotAt, sourceManifest[].retrievedAt
Verification action: Compare the final output with the pack's blockedStatements, sampleReviewOutput.blockedRestatement, escalationTriggers, and actionTaxonomy.stopOrEscalateWhen fields.
Trust boundary: Static public material may explain evidence and limitations, but it must not become live clearance, legal compliance, suitability, safety, guarantee, payment approval, publication approval, or trade advice.
Failure mode: If the output asks a user or agent to move money, publish a financial claim, trust a counterparty, or treat the material as live approval, stop and escalate to human review.
Required citation fields: canonicalCitation.recommendedCitationText, artifactProvenance.artifactVersion, blockedStatements[], sampleReviewOutput.blockedRestatement, escalationTriggers[], actionTaxonomy.stopOrEscalateWhen[]
Cite this pack
Counterparty screening before payment, public-material-counterparty-screening-pack-2026-05-25, generated 2026-05-25T00:00:00.000Z, source snapshot 2026-05-25T00:00:00.000Z, https://trading4ai.com/agent-verification/materials/counterparty-screening-pack
Page: https://trading4ai.com/agent-verification/materials/counterparty-screening-pack
Artifact: https://trading4ai.com/reliability/public-materials/counterparty-screening-pack.json
Source snapshot: 2026-05-25T00:00:00.000Z
Source manifest
URL: /agent-verification/materials/counterparty-screening-pack
Kind: sample_page; role: sample_context; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: beneficiary_mismatch, entity_resolution_fields_missing, instruction_channel_change, beneficiary_proof_missing
Supports: Beneficiary name in the payment draft does not match the previously verified vendor record / Entity-resolution evidence is incomplete across legal name, alias, identifier, country, jurisdiction, and partial-match fields / Updated payment instructions arrived from a domain that was not the previously verified vendor domain / No signed bank letter or portal confirmation ties the new beneficiary account to the claimed counterparty
Limitations:
URL: https://ofac.treasury.gov/sanctions-list-service
Kind: official_registry; role: official_reference; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: ofac_name_search
Supports: OFAC sanctions search returned no exact listed match for the supplied counterparty spelling / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://www.trade.gov/consolidated-screening-list
Kind: official_registry; role: official_reference; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: trade_csl_source_required
Supports: Trade.gov Consolidated Screening List (CSL) review remains required for the supplied counterparty / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://open.gsa.gov/api/exclusions-api/
Kind: official_registry; role: official_reference; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: sam_exclusions_source_required
Supports: SAM.gov exclusions coverage remains required through the public GSA Exclusions API reference / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://www.worldbank.org/en/projects-operations/procurement/debarred-firms
Kind: official_registry; role: official_reference; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: world_bank_debarred_source_required
Supports: World Bank debarred firms review remains required for procurement-style counterparty screening / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://www.cftc.gov/LearnAndProtect/Resources/Check/redlist.htm
Kind: official_registry; role: official_reference; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: cftc_red_list_source_required
Supports: CFTC RED List review remains required when the counterparty is offering trading, investment, or brokerage-like services / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://www.opensanctions.org/
Kind: public_reference; role: primary_warning; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: opensanctions_public_reference
Supports: OpenSanctions can support entity-resolution context, but it is a public aggregator rather than an official clearance source / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
URL: https://consumer.ftc.gov/articles/what-know-about-cryptocurrency-scams
Kind: official_guidance; role: primary_warning; retrieved: 2026-05-25T00:00:00.000Z
Evidence records: ftc_crypto_scam_reference
Supports: FTC cryptocurrency scam guidance remains relevant when the counterparty requests wallet payment or crypto settlement / This is a real high-risk pre-action scenario where static risk review material is more useful than generic trading copy.
Limitations:
Sample bounded output
Verdict: review
The public-source checks do not clear the counterparty, and the beneficiary mismatch keeps the payment in human review.
Safe restatement: Checked selected public sources and sample records at the retrieval time shown; the evidence remains incomplete across alias, identifier, jurisdiction, and no-hit semantics, so the payment stays in review, is not cleared, and is not approved by this pack.
Blocked restatement: This counterparty is safe and the payment can proceed.
Unresolved items
Required follow-up
Review boundaries
These sections turn the pack into a bounded public review aid: what to check, when to escalate, and which statements must stay inside evidence limits.
Review checklist
Escalation triggers
Safe to repeat
Blocked claims
Related public artifacts
Machine-readable
The JSON artifact is the stable machine-facing handoff surface for this pack. It is static, public, and safe to crawl.
Artifact path: /reliability/public-materials/counterparty-screening-pack.json
Use the HTML page for explanation and the JSON artifact for machine retrieval.
Artifact provenance
schemaVersion: trading4ai-public-reliability-v1
artifactVersion: public-material-counterparty-screening-pack-2026-05-25
generatedAt: 2026-05-25T00:00:00.000Z
staticSnapshotAt: 2026-05-25T00:00:00.000Z
artifactUrl: /reliability/public-materials/counterparty-screening-pack.json
Citation fields: artifactVersion, generatedAt, sampleEvidenceRecords[].retrievedAt, sampleReviewOutput.verdict, sourceRefs
When citing this pack, preserve artifactVersion, generatedAt, sampleEvidenceRecords[].retrievedAt, and sourceRefs together.
Do not turn the pack into payment approval, safety clearance, or compliance sign-off.