simplify-code

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes and refactors local code files.
  • Ingestion points: Git diff output and full file contents are read to be processed by review agents (SKILL.md).
  • Boundary markers: There are no explicit markers or instructions provided to the sub-agents to ignore or isolate instructions potentially embedded within the code data.
  • Capability inventory: The skill is designed to directly modify the local filesystem to apply suggested fixes, which is a significant capability when combined with untrusted input.
  • Sanitization: No input validation or content filtering is performed on the code before it is analyzed by the AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 12:37 PM