payabli-vendors

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process vendor data from external API responses (e.g., vendor names, addresses, and transaction summaries). This represents an attack surface where data retrieved from the Payabli API could contain malicious instructions designed to influence the agent's logic.
  • Ingestion points: Data returned from GET /Vendor/{idVendor}, GET /Query/vendors/{entry}, and GET /Query/payouts/{entry}.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the data processed from these API endpoints.
  • Capability inventory: The skill performs network operations (API calls) and reads local configuration files (payabli-integration.md).
  • Sanitization: The instructions do not specify any sanitization, escaping, or schema validation for the data retrieved from the API before it is integrated into the agent's operational context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 05:09 PM