crewai-multi-agent

Warn

Audited by Snyk on Jun 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). SKILL.md describes using CrewAI tools like SerperDevTool and ScrapeWebsiteTool for runtime web search/scraping; scraped page text is ingested into the agent’s LLM context, enabling outsider-authored free text (public web content) to be included.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 29, 2026, 12:55 AM
Issues
1
Security Audit — snyk — crewai-multi-agent