The Agent Skills Directory

[SAFE]: The skill uses the allowed-tools frontmatter field to restrict command execution exclusively to the infsh CLI, limiting the potential attack surface.
[SAFE]: All external references, including documentation links and image assets, point to the vendor's official domain (inference.sh), which is a well-known service in this context.
[SAFE]: Instructions for adding related skills via npx point to the vendor's own repository (inference-sh/skills), representing standard platform functionality.
[SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or unauthorized privilege escalation were detected.

ai-image-generation