contentful

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

• Third-party content exposure detected (high risk: 0.75). The skill delegates to ClawLink/its CLI to fetch Contentful data at runtime (e.g., content types, assets, entries), and that fetched text is then ingested into the agent’s LLM context; since Contentful content is authored by third parties (not the operating user), this is outsider-authored free text via the Contentful API/browser/OAuth path.

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 will fetch and execute remote code from the npm package/registry, e.g. https://www.npmjs.com/package/@useclawlink/cli and interacts with https://claw-link.dev) at runtime, so the external package is a required runtime dependency that executes remote code.