kol-discovery

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 public LinkedIn post content via Apify scrapers based on user-defined keywords, which constitutes outsider-authored social feed text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script accesses https://api.gooseworks.ai as a proxy endpoint for Apify requests, representing an unverified third-party operational service dependency.