code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes
git diffto identify code changes in the repository. This is an expected and legitimate operation for a code review tool. - [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted source code.
- Ingestion points: The skill reads file content and diffs from the local environment (SKILL.md).
- Boundary markers: Absent. The instructions provided to the subagent do not use explicit delimiters or "ignore instructions" warnings to isolate the untrusted code from the analysis logic.
- Capability inventory: The subagent has the capability to analyze code and generate potentially influential reports.
- Sanitization: Absent. There is no evidence of sanitization or escaping of the ingested code before it is passed to the LLM agent.
Audit Metadata