code-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes external code changes, which creates a surface for indirect prompt injection.
  • Ingestion points: Code changes obtained via git diff or directly provided in the code review context.
  • Boundary markers: No specific delimiters or instructions are provided to distinguish between code and embedded instructions in comments.
  • Capability inventory: The skill is restricted to generating text-based review feedback and does not possess network access or file-system writing capabilities.
  • Sanitization: No sanitization or filtering of the input code is defined.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the git diff command to retrieve code changes for analysis, which is a standard read-only operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 05:33 PM