deep-research
Warn
Audited by Snyk on Jul 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). SKILL.md’s required workflow explicitly uses firecrawl_scrape(url) / crawling_exa(url) to fetch and deep-read full web pages at runtime, so outsider-authored free text from arbitrary public URLs is ingested into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata