crewai-multi-agent

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes agents to untrusted public content by assigning web-search and scraping tools (e.g., SerperDevTool, ScrapeWebsiteTool, YoutubeVideoSearchTool, GithubSearchTool in references/tools.md and examples) and using crew.kickoff to ingest and process those external web/YouTube/GitHub search/scrape results as part of agent workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 10:36 PM