intercom-automation

Warn

Audited by Snyk on Feb 20, 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 explicitly fetches and acts on Intercom user-generated content via the Composio/Rube MCP toolkit (e.g., INTERCOM_GET_CONVERSATION, INTERCOM_SEARCH_CONTACTS, INTERCOM_LIST_ALL_ADMINS in the Core Workflows), so untrusted third-party messages could be read and influence replies, assignments, or other agent actions.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill requires calling the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch tool schemas that directly determine the agent's available tools/instructions, making it a required runtime dependency that can control prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 08:19 AM