codebase-documenter
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the target codebase, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads source code, comments, and project documentation through the 'Read' and 'Explore' tools (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions within the code files being analyzed.
- Capability inventory: The skill utilizes 'Read', 'Write', 'Bash', 'Grep', and 'Glob' tools, which could be leveraged if the agent follows malicious instructions hidden in code (SKILL.md).
- Sanitization: There is no validation or sanitization of codebase content before it is processed by the AI.
Audit Metadata