polish-ui
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external project data.
- Ingestion points: The skill instructs the agent to read design context and PRD files from the
plans/directory within the workspace. - Boundary markers: There are no specific instructions or delimiters provided to isolate the ingested file content from the agent's instructions.
- Capability inventory: The skill is intended to guide the agent in modifying frontend source code and design assets.
- Sanitization: No sanitization, escaping, or validation of the content read from the
plans/directory is specified.
Audit Metadata