image-upscaling
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS] The skill references the
beltCLI and associated skills from theinference-shandbelt-shGitHub organizations. These are official sources for the service the skill integrates with. - [COMMAND_EXECUTION] Tool access is restricted to the
beltCLI usingBash(belt *), ensuring the agent can only interact with the intended platform. - [SAFE] The instructions demonstrate standard usage of an AI inference API via its CLI tool. No suspicious patterns such as data exfiltration, prompt injection, or obfuscation were found.
Audit Metadata