crewai-agents

Fail

Audited by Snyk on Feb 15, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E006: Malicious code pattern detected in skill scripts.

  • Malicious code pattern detected (high risk: 1.00). The content includes an unsafe eval() call in the CalculatorTool that can execute arbitrary/untrusted input (risk of remote code execution); no explicit data-exfiltration, credential-theft, obfuscation, or supply-chain indicators were found otherwise.

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

  • Third-party content exposure detected (high risk: 1.00). This skill exposes the agent to untrusted third-party content because its recommended tools include web search and scraping (SerperDevTool, ScrapeWebsiteTool) that fetch and ingest arbitrary public webpages/search results which the agent (e.g., the researcher) is expected to read and interpret.
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 15, 2026, 09:28 PM