video-prompting-guide
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] The skill demonstrates the use of the
beltCLI tool (e.g.,belt app run google/veo-3-1) to perform video generation tasks. This is a primary function of the skill and uses a well-known vendor tool in a transparent manner. - [EXTERNAL_DOWNLOADS] The skill references images and documentation from
inference.sh, which is the provider for the 'belt' CLI and the intended platform for the skill's usage. These are trusted/well-known service references for this context and do not escalate the verdict. - [NO_MALICIOUS_PATTERNS] Analysis of the markdown and example commands reveals no signs of prompt injection, data exfiltration, obfuscation, or privilege escalation.
Audit Metadata