AGENT LAB: SKILLS

apify-market-research

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill runs Apify actors that scrape public sites (e.g., Google Maps, Facebook, Instagram, Booking.com, TripAdvisor) and the runner downloads dataset items from the Apify API (https://api.apify.com/v2/datasets/${datasetId}/items) and prints top results, so it ingests and displays untrusted, user-generated third‑party content as part of its workflow.

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

  • Potentially malicious external URL detected (high risk: 0.80). The skill invokes Apify's APIs at runtime (e.g., POST to https://api.apify.com/v2/acts/{author~actor}/runs?token=...), which starts remote Apify actors (i.e., executes remote code) and the skill requires this API/token to function, so this is a runtime dependency that can execute remote code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 10:24 PM