documentation-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 processes source code to extract docstrings and infer examples, creating a surface where malicious instructions in comments could influence the agent's behavior. 1. Ingestion points: source_path input defined in skill.yaml. 2. Boundary markers: Absent from the provided schema and documentation. 3. Capability inventory: Docstring extraction, Mermaid.js diagram generation, and example inference from tests. 4. Sanitization: Not mentioned in the security considerations.
- No Code (SAFE): The skill package contains only metadata and descriptive markdown files with no executable scripts, which limits the risk of direct malicious actions like data exfiltration or system modification.
Audit Metadata