productboard

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 connect to Productboard and then the agent runs actions/describe/run productboard, which at runtime will fetch and ingest Productboard action metadata and user-facing content (e.g., tickets/notes/fields) that can include outsider-authored free text from other Productboard users; this text is then provided to the agent’s LLM context via the ClawLink CLI.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running "npx @useclawlink/cli" which at runtime fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and interacts with https://claw-link.dev, so external code is executed and is a required dependency.