ahrefs

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

• Third-party content exposure detected (high risk: 0.85). At runtime the skill uses ClawLink to access Ahrefs via browser/OAuth and then ingests Ahrefs-fetched page/content (e.g., SERP/keyword/backlink results) as readable text into the agent’s LLM context, which is outsider-authored web/app content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx @useclawlink/cli (which fetches and executes remote code from the npm package https://www.npmjs.com/package/@useclawlink/cli) and relies on ClawLink (https://claw-link.dev) to supply actions/credentials at runtime, so external content is fetched/ executed and controls agent behavior.