skills/raddue/crucible/ui-verify/Gen Agent Trust Hub

ui-verify

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits vulnerability to indirect prompt injection as it ingests and processes untrusted data from external files that can influence agent behavior.
  • Ingestion points: The skill reads mockup HTML/CSS files from docs/mockups/ and project source files (USS and C#) during the audit process.
  • Boundary markers: No explicit boundary markers or instructions to ignore instructions embedded in the design mockups are provided.
  • Capability inventory: The agent uses mcp__UnityMCP__manage_scene to capture screenshots and is instructed to directly fix implementation code in local files.
  • Sanitization: Content from the ingested mockup and source files is not sanitized or validated before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 10:34 PM