agents-md-generator
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it ingests and processes untrusted data from repository files to generate context for AI agents.
- Ingestion points: The workflow identifies and reads various repository files, including package.json, go.mod, pyproject.toml, Cargo.toml, README.md, Makefile, and CI configurations as specified in SKILL.md.
- Boundary markers: There are no explicit boundary markers or instructions to ignore embedded prompts within the source data being processed.
- Capability inventory: The skill is designed for filesystem-based coding agents with read and write access to the repository root and nested modules.
- Sanitization: The instructions do not include mechanisms for sanitizing or validating content retrieved from the files before it is included in the generated AGENTS.md files.
Audit Metadata