financial-api-integrator

Fail

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill instructions involve the retrieval and use of highly sensitive API keys and OAuth tokens for Stripe, Revolut, PayPal, and cryptocurrency providers.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it ingests external data (invoices and bank statements) to trigger irreversible financial actions. Ingestion points: 'invoice data' and 'bank statement data' specified in SKILL.md. Boundary markers: None mentioned. Capability inventory: 'create_payment', 'initiate_transfer', and currency swap commands. Sanitization: No input validation or sanitization logic is provided.
  • [COMMAND_EXECUTION]: The skill directly triggers financial commands based on automated logic monitoring exchange rates and external invoice data, which could be exploited to move funds without sufficient human oversight.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Apr 18, 2026, 05:56 PM
Security Audit — agent-trust-hub — financial-api-integrator