NYC

UX Designer

Pass

Audited by Gen Agent Trust Hub on Feb 15, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to process external inputs such as user research, personas, and feature requirements. While it lacks explicit input sanitization or boundary markers, it possesses no executable capabilities, file system write access, or network permissions, limiting its impact to internal reasoning influence.
  • Evidence Chain:
  • Ingestion points: manifest.yaml (user_research, personas, feature_requirements)
  • Boundary markers: Absent
  • Capability inventory: None (no executable code provided)
  • Sanitization: Absent
  • [Unverifiable Dependencies] (SAFE): No external packages (npm, pip, etc.) are referenced for installation or execution.
  • [Data Exposure & Exfiltration] (SAFE): The skill does not perform network requests or access sensitive local files.
  • [Prompt Injection] (SAFE): No evidence of system prompt override or safety bypass instructions was detected.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 15, 2026, 09:27 PM