polish
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands for Git operations (git rev-parse, git fetch, git diff, git status, git add, git commit) and GitHub CLI (gh pr view) to manage branch quality and PR metadata.
- [DYNAMIC_EXECUTION]: The simplification rules automatically detect and execute project-specific test runners (e.g., npm test, pytest, go test) found in configuration files like package.json or Makefile to verify that refactors do not break observable behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code from Git diffs and hunks to perform mechanical refactors. While this presents an attack surface, the risk is mitigated by the skill's specific mechanical rules and local-only execution context.
- Ingestion points: rules/simplify.md reads branch changes via git diff.
- Boundary markers: Code content is processed without explicit delimiters or instructions to ignore embedded prompts.
- Capability inventory: The skill can execute shell commands (Git, test runners) and modify files via the Edit tool.
- Sanitization: No sanitization is performed on the diff content before processing.
Audit Metadata