requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes local Git commands (git rev-parse, git log, and git diff) to identify code changes between specific commits. These are standard operations for a development and code review workflow.
  • [PROMPT_INJECTION]: Contains an indirect prompt injection surface where external data such as task descriptions and plan requirements are interpolated into the code-reviewer subagent's instructions.
  • Ingestion points: code-reviewer.md (via {DESCRIPTION} and {PLAN_REFERENCE}).
  • Boundary markers: Absent; the template does not use specific delimiters or instructions to isolate user-provided content from the agent's system instructions.
  • Capability inventory: The subagent executes git diff and git log commands to retrieve codebase data.
  • Sanitization: No validation or sanitization of the interpolated content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 07:40 AM