requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands like
git rev-parse,git log, andgit diffto identify commit SHAs and retrieve code changes for review. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection where malicious instructions could be embedded in the code diffs processed by the subagent.
- Ingestion points: The subagent processes output from
git diffas specified in thecode-reviewer.mdtemplate. - Boundary markers: No explicit delimiters or safety instructions are used to wrap the code content in the review template to distinguish it from reviewer instructions.
- Capability inventory: The agent has the capability to execute
gitcommands and perform subagent task dispatching based on the data processed. - Sanitization: No sanitization or filtering of the code content is performed before it is presented to the LLM.
Audit Metadata