simplifying-code
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided source code, creating an ingestion point for untrusted data. While it contains extensive instructions for ensuring behavior parity and verifying changes, the lack of explicit delimiters for processed content constitutes a vulnerability surface where malicious code could attempt to influence agent behavior.
- Ingestion points: Files and repository content targeted for simplification, refactoring, or AI slop removal in
SKILL.md. - Boundary markers: No specific boundary markers or "ignore embedded instructions" warnings are defined for the code blocks being processed.
- Capability inventory: The skill requires reading and writing files, performing git operations (git blame, worktrees), and executing tests or type checks through the shell.
- Sanitization: No sanitization or escaping logic is provided for the code content; the skill relies on behavioral verification and 'Stop Conditions' to prevent unintended outcomes.
Audit Metadata