ai-avatar-video
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
beltCLI for media processing. It utilizes theallowed-toolsfrontmatter to restrict command execution to thebeltbinary, effectively narrowing the attack surface. - [EXTERNAL_DOWNLOADS]: References an installation script hosted on the
inference-sh/skillsrepository on GitHub. This script is used to set up the necessary CLI environment for the skill's functionality. - [NO_CODE]: The skill does not bundle any local executable scripts or binaries, relying instead on standard instructions and the externally installed CLI tool.
- [DATA_EXPOSURE]: Includes instructions for the standard
belt loginprocedure. No sensitive local files, such as SSH keys or AWS credentials, are accessed or processed by the skill.
Audit Metadata