ux-researcher-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill operates entirely within the local environment. The Python utility
scripts/persona_generator.pywas audited and found to contain only benign heuristic logic using standard libraries to classify research data into user archetypes. It performs no network operations, sensitive file access, or persistent system modifications. - [COMMAND_EXECUTION]: The skill workflow involves executing a local script
scripts/persona_generator.py. This script is part of the skill package and does not accept unsanitized shell input, nor does it spawn sub-processes, making the execution path secure. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a workflow for processing user-supplied research data (JSON format). While this data ingestion represents a potential attack surface for indirect prompt injection, the skill lacks 'sinks' or dangerous capabilities (such as file writing or network exfiltration) that could be exploited by malicious payloads in the research data, rendering the surface safe.
Audit Metadata