apify-brand-reputation-monitoring

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

• Third-party content exposure detected (high risk: 0.90). The skill launches Apify actors to scrape and collect user-generated reviews and comments from public sites (Google Maps, TripAdvisor, Facebook, Instagram, YouTube, TikTok) as described in SKILL.md Step 1/Step 4, then downloads and displays those dataset items via the Apify API in reference/scripts/run_actor.js (downloadResults / displayQuickAnswer), which clearly exposes the agent to untrusted third-party content that could contain injected instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime calls to Apify's API (e.g., https://api.apify.com/v2/acts/{actorId}/runs?token=... and https://api.apify.com/v2/datasets/{datasetId}/items?token=...), which start and poll Apify "actors" (remote code execution) and are required for the skill to function, so external content executes code at runtime.