ai-avatar-video
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches installation instructions from the author's official GitHub repository.
- [COMMAND_EXECUTION]: Uses the belt CLI tool to interact with the inference.sh cloud platform for video generation tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media via URLs, presenting a potential injection surface.
- Ingestion points: Data entering via URLs in the belt app run commands in SKILL.md.
- Boundary markers: Not present in the provided instruction examples.
- Capability inventory: The skill uses network operations to invoke remote AI models for media synthesis.
- Sanitization: No evidence of input validation or sanitization within the skill context.
Audit Metadata