linkedin-message-writer

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow uses Apify to scrape LinkedIn profile data and public posts based on user-supplied URLs, ingesting outsider-authored content (profiles and posts) without prior selection/filtering of individual items.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains cURL commands utilizing endpoints on api.apify.com to invoke remote actors (harvestapi/linkedin-profile-scraper and harvestapi/linkedin-profile-posts) whose instruction and execution payload are fetched at runtime under user-provided configuration, establishing a common/reputable unofficial operational dependency.