social-media-carousel

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the belt CLI tool (associated with the author inf-sh) to perform tasks like user authentication (belt login) and running remote applications (belt app run). These are legitimate uses of the tool within the vendor's ecosystem.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include installing the belt CLI via npx and adding related skills from the author's repository on GitHub (inference-sh/skills). These references point to official vendor resources.
  • [SAFE]: Analysis of the skill body and bash commands revealed no evidence of prompt injection, data exfiltration, persistence mechanisms, or malicious obfuscation. The bash loop used for batch generation is a standard automation pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:34 AM
Security Audit — agent-trust-hub — social-media-carousel