The Agent Skills Directory

[SAFE]: The skill's frontmatter includes an 'allowed-tools' restriction that scopes the environment to only execute commands starting with 'belt', which is a recommended security practice for limiting agent capabilities.
[SAFE]: All external links and resources point to the official domains and repositories of the skill's author, inference-sh (e.g., inference.sh and the inference-sh organization on GitHub).
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found in the instructions or examples.
[EXTERNAL_DOWNLOADS]: The skill mentions external dependencies such as the 'belt' CLI and provides links to its installation guide on the author's GitHub repository. These are standard vendor resources and do not represent a security concern.

image-upscaling