heyreach-automation
Warn
Audited by Snyk on Feb 16, 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 instructs the agent to fetch tool schemas, recommended execution plans, and other metadata from the Rube MCP endpoint (https://rube.app/mcp) via RUBE_SEARCH_TOOLS and then read/interpret those results to drive execution, which exposes the agent to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata