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
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:34 PM