Requesting Code Review
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) as it processes untrusted data from the codebase being reviewed.\n
- Ingestion points: The subagent in
code-reviewer.mdingests code content viagit diffoutput and the{WHAT_WAS_IMPLEMENTED}input variable.\n - Boundary markers: Absent. The template does not use clear delimiters or specific instructions to the agent to treat the diff content as data only and ignore any embedded commands.\n
- Capability inventory: The subagent can execute shell commands (
git diff) and generate reports that influence the development workflow.\n - Sanitization: No sanitization or validation is performed on the code content or the commit SHAs provided to the subagent.\n- [COMMAND_EXECUTION] (SAFE): The skill uses local
gitcommands (git rev-parse,git diff) to identify and analyze changes between commits. This behavior is necessary for the skill's primary purpose and does not involve downloading or executing remote scripts.
Audit Metadata