claude-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/review.pyexecutesgitandclaudecommands to facilitate the code review process. These operations use list-based arguments withsubprocess.run(), which is a secure practice that prevents shell injection attacks by ensuring the shell does not interpret the arguments. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes local repository content, which could theoretically contain malicious instructions designed to influence the agent's behavior. The skill mitigates this risk by implementing a strict
REVIEW_STANDARDsub-agent prompt and explicitly instructing the primary agent to verify all findings independently before applying any changes. - [PRIVILEGE_ESCALATION]: The skill exposes the
claudeCLI's--dangerously-skip-permissionsflag through a--bypass-permissionsoption. The documentation appropriately restricts its use to trusted, isolated environments and explains that it gives the process full system access, ensuring the user is informed of the risk.
Audit Metadata