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 that scrape public, user-generated content from platforms listed in SKILL.md (e.g., Google Maps, TripAdvisor, Facebook, Instagram, YouTube, TikTok) and then downloads and displays those dataset items via the Apify dataset API endpoint (https://api.apify.com/v2/datasets/{datasetId}/items?format=json) as part of its required workflow, so untrusted third-party content is ingested and read by the agent and can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime script calls Apify API endpoints (e.g., https://api.apify.com/v2/acts/${apiActorId}/runs?token=... and https://api.apify.com/v2/datasets/${datasetId}/items?token=...) to start arbitrary Apify actors and fetch results using a required APIFY_TOKEN, which causes remote code (the chosen actor) to execute on Apify at runtime.