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.pyfor 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.pyvia 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