zeno-requesting-code-review
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands, specifically git rev-parse, git log, and git diff, to identify commit ranges and extract code changes for review. These operations are restricted to the local repository context and are necessary for the skill's stated purpose.
- [PROMPT_INJECTION]: The subagent instructions in code-reviewer.md ingest untrusted data from feature descriptions, project plans, and git diff outputs. This creates an indirect prompt injection surface where malicious instructions embedded in the code or documentation could attempt to influence the subagent's evaluation. Ingestion points: Inputs {WHAT_WAS_IMPLEMENTED}, {PLAN_OR_REQUIREMENTS}, {DESCRIPTION}, and git diff output in code-reviewer.md. Boundary markers: None present to isolate external data from the subagent's instructions. Capability inventory: Execution of git commands as defined in SKILL.md and code-reviewer.md. Sanitization: No validation or escaping is applied to the interpolated variables before processing.
Audit Metadata