ux-ui-design
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection (Category 8) due to the ingestion of untrusted external data.
- Ingestion points: The
feedback-analyzer.mdandinterview-guide.mdagents are tasked with analyzing user feedback, app reviews, and interview verbatims, which are sources of external, untrusted content. - Boundary markers: There are no explicit delimiters or system instructions used in the prompt templates to distinguish between agent instructions and the external content being analyzed.
- Capability inventory: The skill is restricted to generating design-related documentation and does not contain dangerous tools or scripts (e.g., network access, arbitrary code execution, or sensitive file manipulation) that could be triggered by a malicious injection.
- Sanitization: No sanitization or validation mechanisms are present for the processed external inputs.
Audit Metadata