ui-research

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to browse and collect data from external design websites, which introduces a surface for indirect prompt injection.\n
  • Ingestion points: External research sources including UI galleries and product sites (e.g., Mobbin, Awwwards, Land-book) during Phase 2 (Research) and Phase 3 (Collect) in SKILL.md.\n
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are provided for handling the summary or extraction of external content.\n
  • Capability inventory: The skill itself lacks dangerous capabilities like shell execution or file-writing, but it generates a design brief intended to guide subsequent implementation tasks.\n
  • Sanitization: No sanitization or validation of the content retrieved from external sites is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:50 PM
Security Audit — agent-trust-hub — ui-research