agentql-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 query an external MCP server (e.g., RUBE_SEARCH_TOOLS against https://rube.app/mcp) to fetch tool slugs, input schemas and execution plans from a third‑party source that the agent must read and interpret, which could contain untrusted or user-provided instructions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires configuring and using the MCP server at https://rube.app/mcp at runtime to discover tool schemas (RUBE_SEARCH_TOOLS) and to execute tools (RUBE_MULTI_EXECUTE_TOOL), so content from that endpoint can directly control agent instructions and trigger remote code execution.
Audit Metadata