requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like
git rev-parseandgit diffto identify and compare specific code changes. These are standard utility operations for its intended purpose of code review. - [PROMPT_INJECTION]: The review subagent analyzes external code changes, which is a surface for indirect prompt injection if the code contains malicious instructions in comments or strings.
- Ingestion points: The agent ingests code changes directly via
git diffoutputs incode-reviewer.md. - Boundary markers: Absent; the template does not use specific markers to isolate the diff content from instructions.
- Capability inventory: The skill uses the
Tasktool to executegitsubcommands. - Sanitization: No sanitization is performed on the code content before it is processed by the subagent.
Audit Metadata