ai-avatar-video
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill content is purely instructional and provides valid examples for interacting with the inference.sh platform. No obfuscation, data exfiltration, or malicious commands were detected.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute 'belt' CLI commands. This usage is consistent with the skill's stated purpose of facilitating AI video generation through that specific tool.
- [EXTERNAL_DOWNLOADS]: The skill references the 'belt-sh/cli' package and points to documentation on GitHub for setup. These are legitimate resources for the platform integrated by the skill.
- [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes user-supplied text scripts and media URLs. Ingestion points: 'voice_script', 'image', and 'audio' fields in Bash examples throughout SKILL.md. Boundary markers: Absent. Capability inventory: Bash tool for CLI command execution. Sanitization: No sanitization steps are documented in the skill instructions.
Audit Metadata