impeccable-polish
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify user-provided code and design assets, which creates a surface for instructions embedded in that data to influence the agent.
- Ingestion points: The skill processes user-supplied projects, source code, and design files specified by the user.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential prompt injections within the target files.
- Capability inventory: The skill instructs the agent to perform file modifications, such as removing console logs and unused imports, which requires read and write access to the workspace.
- Sanitization: No input validation or sanitization mechanisms are defined for the data being processed.
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata without any attached scripts or executables, significantly reducing the direct attack surface.
Audit Metadata