api-document-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and parse untrusted local source code files, which is a vector for indirect prompt injection. 1. Ingestion points: Reads files from specified paths (e.g., src/api/). 2. Boundary markers: None identified in provided documentation. 3. Capability inventory: Reads source files and writes output to the .claude/api_doc/ directory. 4. Sanitization: No sanitization of code comments or strings is mentioned.
- [Metadata Poisoning] (SAFE): Skill metadata is professional and lacks deceptive instructions.
- [Data Exposure & Exfiltration] (SAFE): No sensitive credentials or exfiltration patterns were found; sample outputs use benign placeholder values.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external dependencies or remote execution patterns were found in the provided files.
Audit Metadata