designer-uiux-specialist
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates auditing live web pages, which serves as an entry point for untrusted data into the agent's context.
- Ingestion points: Rendered web pages loaded during the "Fidelity Verification" workflow (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or warnings to prevent the agent from obeying instructions found within the audited web pages.
- Capability inventory: The agent is authorized to use
computer-usetools andevaluate_script(Chrome DevTools MCP) for element inspection. - Sanitization: There are no documented procedures for sanitizing or filtering the content retrieved from external pages before processing.
- [DYNAMIC_EXECUTION]: The workflow specifies the use of script execution within a browser environment to verify design properties.
- Evidence: The "Fidelity Verification" section in SKILL.md explicitly instructs the agent to use
evaluate_scriptto retrieve computed CSS values usingwindow.getComputedStyle(element).
Audit Metadata