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.py executes git and claude commands to facilitate the code review process. These operations use list-based arguments with subprocess.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_STANDARD sub-agent prompt and explicitly instructing the primary agent to verify all findings independently before applying any changes.
  • [PRIVILEGE_ESCALATION]: The skill exposes the claude CLI's --dangerously-skip-permissions flag through a --bypass-permissions option. 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
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:44 AM