git-review
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to interact with Git history via
git logand runs a local Python utilityassets/vigil_report.pyto generate its final output. These operations are required for the skill's primary function of code review and reporting. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to the processing of untrusted external content.
- Ingestion points: The agent reads Git commit logs and raw source code changes as specified in
SKILL.mdandassets/vigil.md. - Boundary markers: Absent. The instructions do not define clear boundaries to distinguish between the agent's instructions and the code/data being analyzed.
- Capability inventory: The agent can execute system commands and Python scripts within the local environment.
- Sanitization: The skill lacks mechanisms to sanitize or escape commit messages and code content before the LLM evaluates them for risks.
Audit Metadata