design-catalog

Warn

Audited by Snyk on Feb 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs fetching and analyzing arbitrary URLs and web content (SKILL.md Step 2: "Screenshot the target via Chrome MCP" when $1 is a route/URL and Step 3: "Research via Gemini (web grounding)"), so untrusted third‑party pages are read and used to drive proposal generation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 09:43 PM