simplify-code
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a rigorous process for code simplification that prioritizes safety and verification. It explicitly warns against dangerous actions like automatic commits, pushes, or repository-wide resets.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external code which could contain malicious instructions.
- Ingestion points: Target source files and symbols named by the user in SKILL.md.
- Boundary markers: Employs 'protected regions' and requires 'explicit behavioural contracts'.
- Capability inventory: Reading and writing local files, executing local tests, linters, and benchmarks.
- Sanitization: Mitigation is achieved through mandatory diff reviews and characterization testing to ensure behavior preservation.
Audit Metadata