lmnt-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 public Rube MCP endpoint (https://rube.app/mcp) and fetching tool schemas and execution plans from composio.dev, i.e., open third-party web content that the agent must read and interpret at runtime, exposing it to untrusted external data that could contain indirect prompt-injection instructions.
Audit Metadata