google-sheets

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

• Third-party content exposure detected (high risk: 0.70). At runtime, the skill uses ClawLink to read Google Sheets cell values (e.g., via googlesheets_values_get / batch_get), and those sheet contents are outsider-authored free text unless the operating user authored them; the LLM ingests the retrieved cell text as prompt context.

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 downloads and executes remote code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli), so it has a runtime external dependency that executes remote code.