linkedin-post-engagers

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly scrapes and ingests public, user-generated LinkedIn content (posts, comments, reactions, profile "about" fields, and company pages) via Apify actors like harvestapi/linkedin-profile-posts and dev_fusion/Linkedin-Profile-Scraper, and then reads and acts on that data (qualification, scraping, enrichment), so untrusted third‑party content can directly influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill relies at runtime on Apify actors (invoked via call-actor and dataset fetches such as "https://api.apify.com/v2/datasets/{DATASET_ID}/items"), which execute remote scraping code on Apify and are required for the pipeline to run.