thumbnail-creator
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests public, user-generated content (YouTube videos via the analyze_video, generate_seo_titles, and generate_seo_description endpoints — and arbitrary image URLs via create_face), so the agent fetches and must read/interpret untrusted third-party content from the open web.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill calls the Thumbnail Creator API at https://app.thumbcraft.io during runtime (e.g., the /videos/analyze endpoint returns "prompt" strings that are then used directly as generation prompts), so fetched content can directly control agent prompts and the skill depends on that API.
Audit Metadata