ux-researcher-designer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Category 8: Indirect Prompt Injection] (SAFE): The skill processes user-provided data (interviews and behavior logs) via a local script. While ingesting untrusted data is a theoretical surface for indirect prompt injection, it is essential to the skill's primary purpose, and no instructions were found to suggest exploitation or lack of sanitization.
- [Category 4: Unverifiable Dependencies & RCE] (SAFE): The skill does not download external scripts or install third-party packages. It relies on a locally defined Python script (
scripts/persona_generator.py). - [Category 10: Dynamic Execution] (SAFE): The skill invokes a local script for its operations, which is standard behavior for agent skills and does not involve runtime compilation of untrusted code or library injection.
Audit Metadata