bootstrap-agents-md
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data (e.g., README files, package.json, and source code) to generate a summary. This presents a potential surface where malicious instructions inside project files could influence the generated documentation.
- Ingestion points: The skill reads
package.json,tsconfig.json,README.md, and scans directory structures usinglsandpwd. - Boundary markers: The skill uses a predefined skeleton and strict rules (e.g., 'no vibes', 'no meta-commentary') to structure the output, which helps mitigate accidental obedience to embedded instructions.
- Capability inventory: The skill utilizes filesystem read/write operations and directory traversal.
- Sanitization: While it does not perform character-level sanitization, it enforces a 'quality bar' that requires claims to be checkable against specific file fields, reducing the likelihood of processing arbitrary injected text as authoritative instructions.
Audit Metadata