refactor-project
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands (
find,grep,wc,npx tsc,npm run lint) to analyze the project structure and verify code integrity during the refactoring process. These commands are scoped to the project directory and align with the skill's functionality.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads source code files from the local project, which serves as an ingestion surface for untrusted data.\n - Ingestion points: Source files in
./components,./app,./hooks, and./types(SKILL.md).\n - Boundary markers: None identified.\n
- Capability inventory: File reading, file writing, and execution of local build/lint tools (
npx,npm).\n - Sanitization: None identified.
Audit Metadata