code-documentation-doc-generate
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and analyze external code, configurations, and comments, which serves as a surface for indirect prompt injection attacks.
- Ingestion points: Code, configuration files, and comments processed by the agent.
- Boundary markers: Absent; there are no specific delimiters used to separate analyzed data from the agent's instructions.
- Capability inventory: No executable scripts (Python or Node.js) are included in this skill.
- Sanitization: The skill includes a basic safety directive to avoid exposing secrets, internal URLs, or sensitive data in the generated documentation.
Audit Metadata