typless-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: 0.90). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the external MCP server (https://rube.app/mcp) and to fetch tool schemas/schemaRefs and execution plans from Composio (e.g., composio.dev), so the agent will ingest and act on arbitrary third-party-provided tool descriptions and metadata.
Audit Metadata