deep-research

Warn

Audited by Snyk on Aug 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The deep-research workflow ingests outsider-authored free text from arbitrary web pages by running firecrawl_search/web_search_exa to select URLs and then firecrawl_scrape/crawling_exa(url) to fetch full page content for reading and synthesis.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 21, 2026, 05:03 AM
Issues
1
Security Audit — snyk — deep-research