linkedin-message-writer

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

• Third-party content exposure detected (high risk: 0.85). The skill uses Apify actors to scrape each lead’s LinkedIn profile and (optionally) recent post text at runtime, and that scraped free-form post body content is then ingested into the agent to generate personalized messages—an outsider-authored source (public LinkedIn posts) via the Apify “dataset items” results.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime calls to Apify (e.g. https://api.apify.com/v2/acts/harvestapi~linkedin-profile-scraper/runs?token=$APIFY_API_TOKEN and https://api.apify.com/v2/acts/harvestapi~linkedin-profile-posts/runs?token=$APIFY_API_TOKEN), and the returned profile/post content is injected into prompts to generate personalized messages while the skill requires the APIFY_API_TOKEN, so external data directly controls the agent's outputs.