thumbnail
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official YouTube documentation for guidance on thumbnail upload dimensions and device-specific size limits.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data which represents an attack surface for indirect prompt injection.
- Ingestion points: Video topics, titles, scripts, and reference images provided by the user as described in SKILL.md.
- Boundary markers: Absent; the agent is instructed to use supplied context and assets directly to construct production briefs.
- Capability inventory: Built-in image generation tool, image viewing tool, and file metadata inspection as referenced in SKILL.md.
- Sanitization: No specific sanitization, filtering, or validation logic for external input is mentioned.
Audit Metadata