code-review-and-commit
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes local shell commands including
git status,git diff,git add, andgit commit. It also suggests running environment-specific validation tools likelintortests. These are essential to the skill's primary purpose but grant the agent the ability to run code on the host system. - [PROMPT_INJECTION] (LOW): Category 8: Indirect Prompt Injection. The skill is vulnerable to instructions embedded within the code it reviews. Ingestion points: The output of
git diffand file contents within the working directory. Boundary markers: No specific delimiters are used to wrap the code content to distinguish it from instructions. Capability inventory: The agent can write to files (applying fixes), stage changes, and execute validation commands (tests/lint). Sanitization: No explicit sanitization or instruction-filtering is performed on the ingested code. - [SAFE]: The skill includes a mandatory 'Approval Gate' (Step 6), requiring explicit user confirmation before staging or committing changes, which significantly mitigates the risk of unauthorized actions.
Audit Metadata