ai-video-generation
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses
allowed-tools: Bash(belt *)to restrict the agent's environment to the specific CLI tool required for its primary purpose. While the wildcard allows all subcommands of thebeltutility, this is standard configuration for a tool-specific skill and does not constitute a security risk in this context. - [SAFE]: Remote references are limited to trusted or well-known documentation and official service domains (inference.sh, github.com). The skill provides command examples that use external media URLs as placeholders, which is consistent with its function as a video generation interface.
- [SAFE]: No evidence of prompt injection, persistence mechanisms, or credential exfiltration was found. The skill follows best practices by instructing users to manage credentials via the
belt logincommand rather than hardcoding secrets.
Audit Metadata