ydc-crewai-mcp-integration

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). This skill connects agents at runtime to You.com's MCP server (https://api.you.com/mcp) and uses the you-search and you-contents tools to fetch and ingest raw content from arbitrary public websites/URLs (as documented in SKILL.md and the examples), which the agent consumes as tool results and thus creates an indirect prompt-injection surface.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill explicitly connects at runtime to https://api.you.com/mcp (via MCPServerHTTP / MCPServerAdapter) to discover and invoke tools and to fetch you-search/you-contents results that are injected into the agent context and can directly control prompts (prompt-injection surface).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 05:07 AM