anthropic-administrator-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the external Rube/Composio MCP (e.g., https://rube.app/mcp) and to ingest tool schemas/arguments returned there, which are untrusted third-party content the agent must read and act on.