BrightData

Warn

Audited by Snyk on Feb 16, 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). This skill explicitly fetches and returns content from arbitrary user-provided web URLs (see Workflows/FourTierScrape.md Step 1 using WebFetch with "URL: [user-provided URL]" and Tier 4 using mcp__Brightdata__scrape_as_markdown), so it ingests untrusted third-party web content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 09:23 AM