do-doc-review
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external documentation files (e.g.,
*-requirements.md,*-plan.md) to perform reviews and edits. - Ingestion points: Reads file content based on invocation paths or files located in the
plans/directory (SKILL.md). - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when reading the target file's content.
- Capability inventory: The skill has the ability to modify local files ("Fix in place") and execute external tools like
plannotator(SKILL.md). - Sanitization: No explicit sanitization or filtering of the document content is described before the agent processes it.
- [COMMAND_EXECUTION]: The skill invokes the
plannotatorCLI tool to facilitate document review. - Evidence:
plannotator annotate <path> --gate --json(SKILL.md). This appears to be an intended workflow tool for the agent's environment.
Audit Metadata