accounts-payable

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could theoretically contain instructions to influence the agent's behavior.
  • Ingestion points: Untrusted data enters the agent context through vendor invoices (PDF, email, EDI, portal), employee expense reports, and vendor setup requests as described in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between data and instructions within the processed documents.
  • Capability inventory: The skill defines capabilities for creating purchase orders, managing vendor banking details, and scheduling payments.
  • Sanitization: The skill lacks automated sanitization or filtering for prompt-based attacks within ingested data, although it mandates procedural checks like verbal callbacks for banking changes.
  • [NO_CODE]: The analyzed skill contains no executable code, scripts, or binary files, consisting solely of markdown instructions and YAML configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:31 AM
Security Audit — agent-trust-hub — accounts-payable