zoho-mail

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the skill uses ClawLink to access Zoho Mail via browser/OAuth and then the agent reads email content (outsider-authored free text from other people’s emails) into the LLM context through the “describe/run” action flow.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes npx @useclawlink/cli at runtime, which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and depends on the ClawLink service (https://claw-link.dev), so external code is executed as a required runtime dependency.