thanks-io-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: 0.80). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the MCP server (e.g., https://rube.app/mcp) and then ingest returned tool slugs, input schemas, and recommended execution plans—dynamic third-party content that the agent must read and act on, which could contain untrusted or user-provided instructions.
Audit Metadata