write-docs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill generates documentation based on codebase context and conversation history, creating a vulnerability surface where malicious code comments or strings could influence the resulting documents.
- Ingestion points: Stage 1 involves gathering context from the current session and the codebase.
- Boundary markers: The skill does not implement specific delimiters or instructions to ignore potentially malicious embedded content within the source context.
- Capability inventory: The skill has the ability to write to files (e.g., README.md, docs/ directory) and invoke sub-agents for testing.
- Sanitization: There is no explicit sanitization or filtering of the gathered context before it is used to draft documentation.
Audit Metadata