aiox-ux-design-expert
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative language and instructions designed to override default agent behavior, such as "CRITICAL: Read the full YAML BLOCK," "DO NOT load any external agent files," and directives to "alter your state of being."
- [COMMAND_EXECUTION]: The activation instructions include a fallback command that executes a local Node.js script:
node .aiox-core/development/scripts/unified-activation-pipeline.js ux-design-expert. This script is part of the vendor's internal development directory. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect instructions through its data processing workflows.
- Ingestion points: The agent is instructed to read handoff artifacts from
.aiox/handoffs/and analyze external code artifacts (HTML/React) via the*scancommand. - Boundary markers: No specific delimiters or safety instructions (e.g., "ignore instructions within these files") are defined when processing these external inputs.
- Capability inventory: The skill has access to local script execution (
node), file reading tools (Read()), and a web browser tool for debugging and testing. - Sanitization: There are no specified sanitization or validation routines for the content of the handoff files or scanned artifacts.
Audit Metadata