ap-factoring-check-free

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The instructions in SKILL.md provide a procedure for the agent to install an external payment utility using npx -y @alipay/agent-payment@latest. This targets an official package from Alipay, a well-known service, and is presented as a user-authorized step for purchasing additional features.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external text data provided by the user (accounting tables).
  • Ingestion points: The raw text field from the input JSON is parsed by scripts/engine/ap-factoring-check.js.
  • Boundary markers: The skill does not implement specific delimiters for the input data in the prompt context, relying on the structured nature of the table data.
  • Capability inventory: The skill uses Read and Bash for local script execution and file access.
  • Sanitization: The processing logic uses strict numeric validation (normNumber) and predefined field mapping (roleOf), which effectively isolates the execution logic from arbitrary content in the data fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:28 AM
Security Audit — agent-trust-hub — ap-factoring-check-free