linkedin-influencer-discovery

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

• Third-party content exposure detected (high risk: 0.70). The skill's discover_influencers.py (run_discovery) starts an Apify actor (powerai/influencer-filter-api-scraper) and then fetches dataset items from the Apify API (https://api.apify.com/.../datasets/{id}/items), ingesting public LinkedIn/profile data (user-generated third-party content) that the agent reads and uses to drive filtering/sorting and potential follow-up actions, so untrusted external content can influence behavior.