agents-md-manager

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes data from untrusted local files to generate documentation.\n
  • Ingestion points: The skill reads from README.md, package.json, project configuration files (e.g., ESLint, Prettier), and project source directories.\n
  • Boundary markers: No delimiters or "ignore instructions" warnings are used when interpolating file content into the agent's context.\n
  • Capability inventory: The skill has the ability to read and write to the filesystem through the read, edit, and project_init tools.\n
  • Sanitization: No evidence of input validation or content filtering was found for the data ingested from project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:32 PM