crewai

Warn

Audited by Snyk on Mar 10, 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's config/agents.yaml explicitly assigns web-search tools (SerperDevTool, WebsiteSearchTool) to the "researcher" agent and the research_task in SKILL.md requires gathering and citing sources, which means the agent will fetch and interpret public web content that can influence downstream task delegation and outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 01:13 AM