ai-video-generation
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external installation guide for its required CLI tool on a public GitHub repository (inference-sh/skills) and suggests adding a skill package via npx.- [COMMAND_EXECUTION]: The skill relies on the 'belt' CLI tool to execute video generation tasks through shell commands as defined in the allowed-tools configuration.- [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by interpolating user-provided prompts directly into CLI command arguments. Ingestion points: Command line arguments in SKILL.md. Boundary markers: None present. Capability inventory: Subprocess execution via Bash(belt *). Sanitization: No input validation or escaping is demonstrated in the examples.- [CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were detected; the skill uses a standard 'login' command for user authentication.
Audit Metadata