refactor-clean
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a
git diffcommand to analyze code change metrics. This is a standard development practice and does not involve unauthorized access or external downloads. - Evidence:
git diff --numstat <base> -- ':!specs' ':!*.test.*' ':!**/test-harness'in SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill operates by refactoring existing source code, which introduces a potential attack surface if the code contains adversarial instructions.
- Ingestion points: Source code files and directories targeted for refactoring (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or guardrails to distinguish between code content and potential instructions.
- Capability inventory: The skill implies the capability to read, modify, and analyze files, including executing local version control commands (
git). - Sanitization: No procedures for escaping or validating the content of the refactored code are mentioned.
Audit Metadata