zendesk

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

• Third-party content exposure detected (medium risk: 0.30). The Zendesk integration reads support tickets and user-submitted content via Zendesk data management workflows, allowing outsider-authored support requests to be ingested by the agent.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes npx @useclawlink/cli, which fetches and runs third-party packages from an unverified external registry without an explicit repository locator or strong first-party provenance.