clickup

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

• Third-party content exposure detected (high risk: 0.85). The skill uses ClawLink to “read and act on” ClickUp data at runtime (e.g., clickup_get_task*, clickup_get_*_comments, clickup_get_view_comments), and those actions ingest outsider-authored free text from ClickUp comments/task descriptions into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs running "npx @useclawlink/cli" at runtime, which fetches and executes remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli), so it has a required external runtime dependency that executes remote code.