Back to skill

Security audit

Sanctions Screening, KYB & AML Compliance

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent compliance-screening purpose, but it sends sensitive person and company identifiers to a third-party paid API and describes automatic USDC payments without clear consent or spending controls.

Install only if you are comfortable sending screened person, company, domain, or wallet identifiers to GoCreative's API and paying per request in USDC. Use explicit approvals for each screening run, avoid confidential or regulated data unless you have a lawful basis and privacy review, set wallet spending limits outside the skill, and do not enable periodic monitoring without a defined budget and stop condition.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:28
Finding

Sensitive KYC and KYB Identifiers Disclosed Through Third-Party GET URLs

Content
View full analysis
Remediation
View remediation

other

Warning
Location
SKILL.md:20
Finding

Automatic USDC Payments Lack Explicit Approval and Spending Controls

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger guidance is broad enough to activate on generic decisions such as whether an entity is 'legit', 'safe', or appropriate to transact with. In practice this can cause the skill to engage in many common workflows and send sensitive names, domains, or counterparties to an external screening API unexpectedly, expanding data exposure and paid-call risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill encourages screening people and companies but does not clearly warn that submitted names, domains, and entity identifiers are transmitted to a third-party paid service. Because these inputs may contain personal data, customer onboarding details, or sensitive counterparty information, users may disclose regulated or confidential data without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

This endpoint transmits a target company/domain to an external provider to obtain a compliance verdict. Even though the behavior is the purpose of the skill, it creates a real confidentiality and privacy boundary crossing and can expose sensitive onboarding or transaction counterparties to a third party.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
| Call | What you get | Price |
|---|---|---|
| `GET https://api.gocreativeai.com/v1/compliance/verdict/{target}` | **One PASS / WARN / BLOCK** decision, fusing sanctions + PEP + risk. Best first call. | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/data/sanctions-screen/{name}` | Matches across **OFAC, EU, UK, UN** sanctions + **PEP** + watchlists | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/bundle/kyb-360/{company}` | **Full KYB**: sanctions/PEP/watchlist + 0-100 risk + business registry | ~$0.45 |
| `GET https://api.gocreativeai.com/v1/risk/entity-score/{company}` | Fused **0-100 risk score** (OFAC + CFPB + legal-entity) | ~$0.05 |

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This sanctions-screen endpoint sends a person or entity name to an external API, which may include personal data or highly sensitive watchlist-screening context. Such transmission can create privacy, compliance, and confidentiality issues if performed automatically or without adequate notice.

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
| Call | What you get | Price |
|---|---|---|
| `GET https://api.gocreativeai.com/v1/compliance/verdict/{target}` | **One PASS / WARN / BLOCK** decision, fusing sanctions + PEP + risk. Best first call. | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/data/sanctions-screen/{name}` | Matches across **OFAC, EU, UK, UN** sanctions + **PEP** + watchlists | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/bundle/kyb-360/{company}` | **Full KYB**: sanctions/PEP/watchlist + 0-100 risk + business registry | ~$0.45 |
| `GET https://api.gocreativeai.com/v1/risk/entity-score/{company}` | Fused **0-100 risk score** (OFAC + CFPB + legal-entity) | ~$0.05 |
| `GET https://api.gocreativeai.com/v1/risk/vendor/{company}` | Vendor dossier: **GLEIF** legal entity + OFAC + CFPB complaints | ~$0.05 |

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The KYB-360 endpoint sends company identifiers to an external service for a full due-diligence report. This can reveal sensitive commercial relationships, onboarding plans, or investigative activity to the provider, which is a meaningful external data exposure risk.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
|---|---|---|
| `GET https://api.gocreativeai.com/v1/compliance/verdict/{target}` | **One PASS / WARN / BLOCK** decision, fusing sanctions + PEP + risk. Best first call. | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/data/sanctions-screen/{name}` | Matches across **OFAC, EU, UK, UN** sanctions + **PEP** + watchlists | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/bundle/kyb-360/{company}` | **Full KYB**: sanctions/PEP/watchlist + 0-100 risk + business registry | ~$0.45 |
| `GET https://api.gocreativeai.com/v1/risk/entity-score/{company}` | Fused **0-100 risk score** (OFAC + CFPB + legal-entity) | ~$0.05 |
| `GET https://api.gocreativeai.com/v1/risk/vendor/{company}` | Vendor dossier: **GLEIF** legal entity + OFAC + CFPB complaints | ~$0.05 |

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

This risk-scoring endpoint sends company information externally, disclosing who the user is evaluating and potentially exposing internal due-diligence interests. While not inherently malicious, it is a real data-sharing event with potential privacy and business-sensitivity consequences.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
| `GET https://api.gocreativeai.com/v1/compliance/verdict/{target}` | **One PASS / WARN / BLOCK** decision, fusing sanctions + PEP + risk. Best first call. | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/data/sanctions-screen/{name}` | Matches across **OFAC, EU, UK, UN** sanctions + **PEP** + watchlists | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/bundle/kyb-360/{company}` | **Full KYB**: sanctions/PEP/watchlist + 0-100 risk + business registry | ~$0.45 |
| `GET https://api.gocreativeai.com/v1/risk/entity-score/{company}` | Fused **0-100 risk score** (OFAC + CFPB + legal-entity) | ~$0.05 |
| `GET https://api.gocreativeai.com/v1/risk/vendor/{company}` | Vendor dossier: **GLEIF** legal entity + OFAC + CFPB complaints | ~$0.05 |

`{target}`/`{company}` = a domain (e.g. `stripe.com`) or legal name; `{name}` = a person or entity name (URL-encode spaces).

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The vendor-risk endpoint transmits a company identifier to a third party, which can disclose vendor evaluation activity and associated business context. In procurement and compliance settings, those details may be sensitive and should not be sent silently or by broad auto-activation.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
| `GET https://api.gocreativeai.com/v1/data/sanctions-screen/{name}` | Matches across **OFAC, EU, UK, UN** sanctions + **PEP** + watchlists | ~$0.15 |
| `GET https://api.gocreativeai.com/v1/bundle/kyb-360/{company}` | **Full KYB**: sanctions/PEP/watchlist + 0-100 risk + business registry | ~$0.45 |
| `GET https://api.gocreativeai.com/v1/risk/entity-score/{company}` | Fused **0-100 risk score** (OFAC + CFPB + legal-entity) | ~$0.05 |
| `GET https://api.gocreativeai.com/v1/risk/vendor/{company}` | Vendor dossier: **GLEIF** legal entity + OFAC + CFPB complaints | ~$0.05 |

`{target}`/`{company}` = a domain (e.g. `stripe.com`) or legal name; `{name}` = a person or entity name (URL-encode spaces).