shippo

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 “find/describe/run” Shippo actions, which at runtime necessarily fetches Shippo action metadata and/or results from Shippo’s service (outsider-authored free text via the Shippo API/browser/OAuth-backed responses) into the agent’s LLM context.

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 fetches and executes remote code from the npm registry (see https://www.npmjs.com/package/@useclawlink/cli), so a runtime-fetched external package directly executes code the agent relies on.