dromo-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 (e.g., https://rube.app/mcp) and to ingest returned tool schemas and "recommended execution plans" for runtime decision-making, which are untrusted third-party responses the agent must read and follow.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill requires configuring and calling an MCP runtime at https://rube.app/mcp (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL), which is used at runtime to execute remote tools/commands and thus directly causes remote code execution from that endpoint.
Audit Metadata