remote-retrieval-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 requires calling RUBE_SEARCH_TOOLS against the external Rube MCP endpoint (https://rube.app/mcp) to retrieve tool schemas and recommended execution plans—third-party dynamic content the agent must read and act on, which could carry indirect prompt-injection instructions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill instructs adding the MCP endpoint https://rube.app/mcp to the client and then calls RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL against that service at runtime to discover tool schemas and execute remote tools, meaning this URL is a required runtime dependency that can control agent instructions and execute code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:56 PM