intercom-automation

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md describes Intercom tool calls (list/search/get/reply) where conversation/contact body text is handled only as first-party user-supplied inputs (e.g., body), and it does not indicate any required workflow that ingests arbitrary outsider-authored free text from an open feed without first selecting a specific item.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). This skill instructs the agent to add and use https://rube.app/mcp as an MCP server and to call RUBE_SEARCH_TOOLS at runtime to fetch current tool schemas from that endpoint, which directly controls available tools/instructions for the agent.