docmosis-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). This skill instructs the agent to call RUBE_SEARCH_TOOLS against an external MCP server (e.g., https://rube.app/mcp and https://composio.dev/toolkits/docmosis) to fetch tool schemas and execution plans, so the agent will ingest and act on potentially untrusted third-party content.
Audit Metadata