skills/djalmajr/skills/ux-persona/Gen Agent Trust Hub

ux-persona

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's core functions, such as browser interaction and report generation, are performed for the legitimate purpose of UI/UX auditing as described in the documentation.
  • [PROMPT_INJECTION]: The skill processes untrusted flow and persona files, which represents an indirect prompt injection attack surface. (1) Ingestion points: Flow files (e2e/flows/.md) and persona files (e2e/personas/.md). (2) Boundary markers: The skill does not define specific boundaries or ignore-instructions for the processed data. (3) Capability inventory: Access to browser automation tools and file writing for reports. (4) Sanitization: No input validation or sanitization is performed on the content of the ingested files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 01:23 PM
Security Audit — agent-trust-hub — ux-persona