generate-agents-md-for-repository

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected. The skill reads external, potentially untrusted data from repository files and manifest files to generate an AGENTS.md file.
  • Ingestion points: The skill reads README.md, pyproject.toml, package.json, and other config files in the project root to infer project details.
  • Boundary markers: No specific delimiters or instructions to ignore instructions embedded in the source files are provided.
  • Capability inventory: The skill has the ability to write or overwrite the AGENTS.md file in the project's root directory.
  • Sanitization: The skill does not implement sanitization or filtering of the content read from the project files before processing it for output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:12 AM