request-refactor-plan
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a benign conversational workflow for project management and planning.
- [DATA_EXFILTRATION]: The skill facilitates publishing information to external project management tools (GitHub via gh CLI and Linear via MCP). These operations are part of the core functionality and target well-known services.
- [PROMPT_INJECTION]: Instructions are focused on a structured refactoring workflow and do not contain patterns aimed at bypassing agent constraints or overriding system behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes repository content to inform the refactor plan. While the skill ingests untrusted data from the codebase, the capabilities are limited to planning and documentation, preventing the execution of malicious instructions found in files.
Audit Metadata