ai-model-expert-drama-comedy-genre
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides several Python scripts, such as
blueprint.py,imagegen.py, andvideogen.py, which are intended to be executed via the command line to manage video production workflows and interact with the AI-HIVE platform. - [EXTERNAL_DOWNLOADS]: The generation scripts are designed to download generated image and video assets from the official AI-HIVE API domain (
ai-hive.iclip.cn) upon task completion. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided prompts that are sent to external AI models for media generation, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Prompts, project goals, and audience descriptions are accepted as command-line arguments in
blueprint.py,imagegen.py, andvideogen.py. - Boundary markers: None identified; the scripts pass user-supplied strings directly to the platform API.
- Capability inventory: The skill includes the ability to perform network requests to the vendor API and write generated files (images, videos, and JSON blueprints) to the local file system.
- Sanitization: No explicit validation or escaping is performed on the user-provided prompt strings before they are transmitted to the remote models.
Audit Metadata