aesthetic

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's Workflow 1 explicitly instructs the agent to browse public inspiration sites (Dribbble, Mobbin, Behance, Awwwards) and use the chrome-devtools and MCP integrations to capture and analyze screenshots from those open web pages, which the agent then interprets to drive design decisions and iterative tool actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 01:09 AM