simplify
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
git diffto identify changes in the repository. This is an expected command for the stated purpose of code review. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted data and has significant capabilities.
- Ingestion points: Untrusted code changes are pulled into the context via
git diffas specified inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present to protect the agent from malicious instructions within the diff.
- Capability inventory: The skill allows the agent to "fix each issue directly," which implies file-writing permissions across the codebase.
- Sanitization: There is no evidence of sanitization or validation of the input data before the agent acts upon it.
Audit Metadata