ai-brand-kit
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents how to interact with the each::labs API via standard
curlcommands and the OpenAI Python SDK. All network operations target well-known or vendor-specific endpoints (eachlabs.run, eachlabs.ai). - [SAFE]: The skill correctly instructs users to use environment variables (
$EACHLABS_API_KEY) or placeholders (YOUR_EACHLABS_API_KEY) for authentication, preventing hardcoded credentials. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided brand descriptions and image URLs. However, it lacks dangerous capabilities like local file writes or arbitrary system command execution, and uses standard multimodal message formatting, presenting a minimal attack surface.
Audit Metadata