dub

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow invokes the ClawLink CLI to fetch Dub action metadata (e.g., via npx @useclawlink/cli actions dub / describe dub), which is outsider-authored free text coming from Dub’s service responses over the network and then ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs running npx @useclawlink/cli (https://www.npmjs.com/package/@useclawlink/cli), which at runtime fetches and executes remote npm package code, so it is a required external dependency that runs remote code.