classmarker-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 external MCP endpoints (e.g., RUBE_SEARCH_TOOLS against the public MCP server at https://rube.app/mcp and RUBE_GET_TOOL_SCHEMAS) to fetch tool schemas, execution plans and pitfalls that the agent must read/interpret at runtime, exposing it to untrusted third-party content.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires contacting the MCP server at https://rube.app/mcp at runtime to discover tool schemas (RUBE_SEARCH_TOOLS) and invoke tools (RUBE_MULTI_EXECUTE_TOOL), meaning content from that URL directly controls execution instructions and causes remote code/tool execution, and is a required runtime dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:36 AM