test-unit

Warn

Audited by Snyk on Jul 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). Yes—runtime calls to outsider-authored public web content via Firecrawl (CallMcpTool with user-firecrawlfirecrawl_search/firecrawl_scrape) ingest scraped markdown into the agent’s LLM context, enabling indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 24, 2026, 11:20 AM
Issues
1
Security Audit — snyk — test-unit