frontend-ui-ux
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (SAFE): No explicit patterns for prompt injection or safety bypasses were detected in the skill instructions.
- Indirect Prompt Injection (LOW): The skill is a conduit for untrusted user input which is passed to downstream agents and tools without sanitization. 1. Ingestion points: The {{ARGUMENTS}} variable in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Delegation to the 'designer' subagent and 'mcp__g__ask_gemini' tool. 4. Sanitization: Absent.
Audit Metadata