wrike

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

• Third-party content exposure detected (medium risk: 0.65). At runtime, the skill uses ClawLink to drive a browser/OAuth connection to Wrike and then fetches Wrike action lists/descriptions and other task content (outsider-authored free text from Wrike’s web/app UI) into the agent’s context via the ClawLink CLI.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run "npx @useclawlink/cli" (see https://www.npmjs.com/package/@useclawlink/cli), which fetches and executes remote npm code at runtime and is a required dependency for the skill.