redesign
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze existing UI components and layouts, which serves as a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Reads project source code (e.g., React and Tailwind components) from the repository for inspection.
- Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded natural language instructions within the code comments or strings.
- Capability inventory: The skill allows the agent to modify files in the repository and execute UI verification workflows.
- Sanitization: No sanitization or filtering is performed on the ingested code content before it is processed by the agent.
Audit Metadata