freshdesk

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to access Freshdesk and then the agent reads ticket/contact/company content via the Freshdesk integration (outsider-authored support data from other users/customers) into the LLM context when describing/running actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running remote code at runtime via npx (npx @useclawlink/cli), which fetches and executes the @useclawlink/cli package from the npm registry (see https://www.npmjs.com/package/@useclawlink/cli) and thus directly executes external code the agent relies on.