docs-specialist
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core functionality involves ingesting and acting upon untrusted data from source code and comments.
- Ingestion points: The
SKILL.mdfile directs the agent to 'Scan code files', 'Extract structure', and 'Parse existing comments (JSDoc, docstrings)'. - Boundary markers: The skill lacks instructions or delimiters to ensure the agent ignores natural language instructions that might be embedded within the comments or files it parses.
- Capability inventory: The skill allows the agent to modify the codebase and documentation files, specifically via the
/docs-specialist:sync fixcommand and documentation generation tasks. - Sanitization: There is no requirement or process defined for sanitizing or validating the extracted content before it is processed by the LLM.
Audit Metadata