freshbooks

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses ClawLink to access the user’s FreshBooks account via OAuth and then the agent reads FreshBooks data (e.g., lists of businesses/clients/projects/journal entries) which is outsider-authored business/account content not authored by the operating user, and that readable text is ingested into the agent’s LLM context through the tool outputs.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run npx @useclawlink/cli which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and relies on that package at runtime.