intercom

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses ClawLink to “read” Intercom data and then the agent uses that retrieved Intercom content in its LLM context; since Intercom messages/articles/conversations are authored by other people (customers/agents), this is outsider-authored free text entering the model via the Intercom read/describe/run paths.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running "npx @useclawlink/cli" which fetches and executes remote code from the CLI package (e.g. https://www.npmjs.com/package/@useclawlink/cli) at runtime, and that external code controls agent actions and credentials, so it is a required runtime dependency that executes remote code.