docnify-automation

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 Rube MCP (e.g., https://rube.app/mcp and composio.dev/toolkits/docnify) to fetch live tool schemas and execution plans that the agent is expected to read and act on, exposing it to externally supplied (third‑party) content that could carry malicious instructions.