generar-readme
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts information from project files (manifests, PRDs, ADRs, and source code) to populate a README template. Maliciously crafted content in these repository files could potentially be used to influence the agent's output during the generation process.
- Ingestion points: Project manifests (package.json, pyproject.toml, requirements.txt, Cargo.toml), docker-compose.yml, PRD.md, TECH-DESIGN.md, ADR files, and source code files searched via grep.
- Boundary markers: There are no specific instructions to use delimiters or ignore instructions found within the analyzed files.
- Capability inventory: The skill utilizes filesystem read capabilities to analyze the project and filesystem write capabilities to create or update the README.md file.
- Sanitization: The skill lacks explicit instructions to sanitize or validate the content extracted from external files before incorporating it into the final document.
Audit Metadata