autobound-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: 0.70). The skill explicitly calls external endpoints (e.g., RUBE_SEARCH_TOOLS against the Rube MCP at https://rube.app/mcp and references composio.dev/toolkits/autobound) to fetch tool schemas, execution plans, and arguments from public third-party sources which the agent must read and act on at runtime, creating a clear avenue for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:26 AM