cs-refactor-ff
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill defines a narrow, low-risk process for refactoring that is restricted to single-file changes under 100 lines. It includes explicit checks to ensure that program behavior is not altered during the optimization.
- [COMMAND_EXECUTION]: The instructions direct the agent to use local development tools for verification, specifically running unit tests, integration tests, type checks, linters, and grep. These are standard developer operations performed within the local project context to ensure code quality.
- [PROMPT_INJECTION]: The skill processes user-supplied prompts and local source code, creating a surface for indirect prompt injection (Category 8).
- Ingestion points: Source code files targeted for refactoring and user-provided optimization instructions (SKILL.md).
- Boundary markers: The skill requires an 'Alignment' step where the agent must summarize its plan and obtain user confirmation before applying any changes.
- Capability inventory: The agent can write modified code to the file system and execute shell commands for testing and verification.
- Sanitization: The skill limits modifications to a predefined list of 'Classic Refactoring Methods' (e.g., Extract Function, Guard Clauses), which serves as a logical constraint against generating arbitrary or malicious code.
Audit Metadata