zoho-bigin

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow uses ClawLink to “run” Zoho Bigin actions via browser/OAuth, which at runtime will fetch Zoho Bigin record text (e.g., CRM fields, notes, emails) authored by other people and feed it into the agent’s LLM context through the tool’s returned readable content.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill instructs the agent to run "npx @useclawlink/cli", which fetches and executes remote npm package code at runtime (see https://www.npmjs.com/package/@useclawlink/cli), so external code is executed and controls the agent's actions.