ux-audit-rethink
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, including live URLs, screenshots, and user feedback, which provides a surface for indirect prompt injection attacks.
- Ingestion points: The
Inputs Requiredsection specifiesscreenshots_or_linksanduser_feedbackas data sources for the agent to process. - Boundary markers: The instructions do not explicitly define delimiters (e.g., XML tags or clear labels) to separate the external data from the agent's core instructions.
- Capability inventory: The skill's capabilities are primarily focused on textual analysis, report generation, and design recommendations. No scripts or commands for automated file system manipulation or network exfiltration are provided.
- Sanitization: There are no instructions for the agent to sanitize, filter, or ignore instructions that may be embedded within the external screenshots or linked content.
Audit Metadata