app-integrations

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow allows the agent to read emails, Slack messages, and GitHub issues/PRs via ClawLink integrations, which ingest outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of packages from an arbitrary third-party registry (npx @useclawlink/cli) whose ownership and publisher provenance cannot be verified as an official vendor, presenting a high risk unknown dependency.