competitive-social-listening

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly scrapes public, user-generated LinkedIn pages and comments via apify_run_actor (harvestapi/linkedin-company-posts) and dropleads_search_people — see SKILL.md Steps 2–4 and scripts/competitive_social_listening.py where the agent downloads posts, reactions and comment text and then uses that content to decide which posts to batch/scrape and to build prospecting outputs — so untrusted third-party content is ingested and can materially influence workflow.