skills/leonxlnx/taste-skill/brandkit/Gen Agent Trust Hub

brandkit

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions and design principles meant to guide an AI's image generation output. There are no executable scripts, shell commands, or network operations.
  • [NO_CODE]: No code or external dependencies are included. The functionality is purely prompt-based, defining visual styles, layout structures, and brand strategy metaphors for creative tasks.
  • [INDIRECT_PROMPT_INJECTION]: While the skill instructions specify how to process user-provided references, the attack surface is limited to the generation of image prompts. There is no evidence of capability for file system access, credential theft, or remote command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 09:10 PM
Security Audit — agent-trust-hub — brandkit