ux-researcher-designer

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions to execute a local Python script scripts/persona_generator.py for processing user research data. This is a standard functional component provided within the skill package.
  • [PROMPT_INJECTION]: The skill features an indirect prompt injection surface in Workflow 1 where it ingests untrusted user data (JSON).
  • Ingestion points: User-supplied research data (JSON) in SKILL.md (Workflow 1).
  • Boundary markers: Absent; the workflow does not define specific delimiters for the input data.
  • Capability inventory: Execution of scripts/persona_generator.py via subprocess call.
  • Sanitization: Absent; the skill does not specify validation or escaping for the ingested JSON fields. Despite this surface, the context is strictly functional and lacks malicious patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — ux-researcher-designer