document-work
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes local git commands like git log and git diff to analyze project history and code changes.
- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection as the skill ingests and processes untrusted data from git history and codebase files to generate documentation.
- Ingestion points: Phase 1 reads data from the output of git log and git diff commands into the agent context.
- Boundary markers: The skill does not define explicit delimiters or instructions to prevent the agent from obeying commands embedded in the ingested data.
- Capability inventory: The skill is capable of writing markdown files to the local project structure, including patterns.md and files in the memory/ directory.
- Sanitization: The workflow relies on a manual Phase 4 checklist for quality and security instead of automated data sanitization.
Audit Metadata