instagram

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

• Third-party content exposure detected (medium risk: 0.30). The workflow monitors and consumes Instagram comments and messages, which can contain outsider-authored free text submitted directly to the user's social media accounts.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of external package npx @useclawlink/cli from an unknown third-party registry without verifiable first-party provenance, constituting a weak-provenance operational dependency.