instagram

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the skill uses ClawLink to perform browser/OAuth-based Instagram operations and then ingests Instagram-fetched page/content (e.g., user info, media, comments, insights) as readable text into the agent’s context, which is outsider-authored free text from Instagram.

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 package https://www.npmjs.com/package/@useclawlink/cli and interacts with https://claw-link.dev) at runtime, so external code is fetched/executed and is required for the agent to perform its actions.