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 instructions and the reviewer template utilize shell commands such as git rev-parse, git log, and git diff to identify, analyze, and stat code changes. These are standard operations for development-focused skills.
  • [PROMPT_INJECTION]: The code-reviewer.md template instructs the subagent to process and analyze the output of git diff. This creates a surface for indirect prompt injection where malicious instructions embedded in the code being reviewed could attempt to deceive the reviewer.
  • Ingestion points: Code changes enter the subagent context via {BASE_SHA} and {HEAD_SHA} parameters in the git diff command in code-reviewer.md.
  • Boundary markers: The prompt lacks explicit delimiters or instructions to the LLM to ignore or isolate instructions found within the code diff content.
  • Capability inventory: The subagent is designed to produce a technical report and assessment but does not appear to possess tools for code execution or network access.
  • Sanitization: There is no evidence of sanitization or filtering of the code content before it is processed by the reviewer subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 11:15 AM