component-refactoring
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
pnpm(e.g.,pnpm refactor-component,pnpm analyze-component) to analyze code and generate refactoring prompts. These scripts appear to be vendor-specific tools for the Dify project. Note thatrefactor-componentis documented to automatically copy output to the system clipboard on macOS. - [PROMPT_INJECTION]: There is a potential for indirect prompt injection as the skill reads source code from the filesystem and incorporates it into prompts for the AI. Malicious instructions embedded in the code being refactored could influence the agent's actions.
- Ingestion points: React component source files provided by the user or identified by the agent.
- Boundary markers: No specific delimiters or safety instructions are mentioned for handling the ingested code content.
- Capability inventory: The skill involves reading files, executing local scripts, and generating new AI prompts.
- Sanitization: The documentation does not describe any validation or sanitization of the input source code before processing.
Audit Metadata