NYC

ux-researcher-designer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill ingests user data and interviews for analysis, which are untrusted inputs. Evidence: 1. Ingestion points: User data passed as a JSON argument to persona_generator.py. 2. Boundary markers: Absent in documentation. 3. Capability inventory: Execution of persona_generator.py script. 4. Sanitization: Not specified in the skill description.
  • [Remote Code Execution] (SAFE): No remote script downloads or piped bash commands were detected.
  • [Data Exposure] (SAFE): No hardcoded credentials, API keys, or access to sensitive system file paths were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:54 PM