ai-explainer-video
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill documentation and code examples focus exclusively on legitimate usage of the each::labs video generation service. All tool usage (Bash/curl) and network targets are aligned with the skill's primary purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection via user-provided prompts and external image URLs.
- Ingestion points: Content provided in the user role and external URLs passed in the image_url field in SKILL.md.
- Boundary markers: The examples do not utilize system-level delimiters or warnings to ignore instructions embedded in the user content.
- Capability inventory: The skill has network access capabilities via the Bash(curl) tool.
- Sanitization: There is no evidence of sanitization or structural validation for the external content before it is passed to the AI model.
Audit Metadata