refine
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of natural language instructions guiding the AI to act as a UI/UX expert. It focuses on design principles like color de-noising, layout optimization, and typography hierarchy without requesting any sensitive permissions or tool access.\n- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for processing untrusted UI descriptions or code.\n
- Ingestion points: UI descriptions or code provided as input in the SKILL.md execution context.\n
- Boundary markers: Absent; there are no instructions to the agent to disregard commands embedded within the provided UI data.\n
- Capability inventory: None; the skill does not have any shell, network, or file system access, nor does it use external tools.\n
- Sanitization: Absent.
Audit Metadata