generate-agents-md

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and synthesizes information from external, potentially untrusted project files.
  • Ingestion points: The workflow involves reading files such as package.json, pyproject.toml, go.mod, Cargo.toml, README.md, and CONTRIBUTING.md to extract conventions.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded prompts within the source files are defined for the generation of the AGENTS.md file.
  • Capability inventory: The skill possesses the capability to read project configuration files and write to a new file (AGENTS.md) in the project root.
  • Sanitization: There is no explicit sanitization or filtering of the text extracted from the project documentation before it is incorporated into the instructions meant for future agent sessions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 08:34 AM