brand-visual-generator
v1.4.0When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user ment...
⭐ 0· 162·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description match the instructions: guidance on typography, color, spacing, design tokens, and mapping palettes for slides/front-end. The SKILL.md's references to slide theming, CSS variables, and design tokens are coherent with a brand-visual tool.
Instruction Scope
Instructions are prose-only guidance and checklist-style recommendations. It asks the agent to read project context files if present (.claude/project-context.md or .cursor/project-context.md Section 12) to gather brand context — this is relevant for producing tailored brand guidance. No instructions were found that request unrelated system files, credentials, or external exfiltration.
Install Mechanism
No install spec or code files; instruction-only skills have minimal disk/write risk. There are no downloads, extracted archives, or package installs declared.
Credentials
The skill declares no required environment variables, credentials, or config paths. Any environment/context reading (project-context files) is proportionate to producing brand-specific recommendations.
Persistence & Privilege
always is false and there is no request to modify agent-wide settings or other skills. Autonomous invocation is allowed by default, which is normal; the skill does not request permanent elevated privileges.
Assessment
This is an instruction-only branding helper and appears internally consistent. Before installing or invoking: (1) be aware the skill will look for project-context files (.claude/project-context.md or .cursor/project-context.md) if present — remove or sanitize those files if they contain secrets or proprietary assets you don't want the agent to read; (2) it does not request credentials or install code, so it won’t add binaries to your system; (3) avoid pasting highly confidential images/brand assets into the chat if you do not want them processed; and (4) if you need strict isolation, test the skill on a non-sensitive project or in a sandboxed environment first.Like a lobster shell, security has layers — review code before you run it.
latestvk979ppysgq7yndx01n3vacwmvs83s1ma
License
MIT-0
Free to use, modify, and redistribute. No attribution required.