afrexai-ux-research-engine
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (SAFE): The provided files (README.md and _meta.json) contain documentation and metadata only. No executable scripts, Python code, or Node.js logic were found within the skill files.
- [PROMPT_INJECTION] (LOW): The skill is designed to process external, untrusted data such as 'interview notes' and 'user feedback', creating an indirect prompt injection surface. 1. Ingestion points: User-supplied interview notes and feedback data as described in the README features. 2. Boundary markers: No delimiters or 'ignore instructions' warnings are present in the provided documentation. 3. Capability inventory: No code-based capabilities (e.g., subprocess execution, network operations) were identified in the analyzed files. 4. Sanitization: No input sanitization or filtering logic is documented.
Audit Metadata