revolt-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 an external MCP server (https://rube.app/mcp) and ingest returned tool slugs, schemas, and recommended execution plans from that third‑party endpoint, which the agent will read and act on and thus could carry untrusted/remote instructions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the MCP server at https://rube.app/mcp at runtime to discover tool schemas and invoke RUBE_MULTI_EXECUTE_TOOL, so remote content from that URL directly controls the agent's instruction construction and triggers remote code execution.
Audit Metadata