ux-audit
Warn
Audited by Snyk on Mar 18, 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 the agent to crawl and fetch arbitrary public websites (user-provided URLs) using Exa MCP / WebFetch / WebSearch (see SKILL.md "Prerequisites — web crawling tool" and "Step 1. Data collection"), and it ingests and interprets that untrusted third‑party page content to produce audit findings and drive recommendations.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata