ClawHub

navigation-menu-generator

v1.0.1

When the user wants to design, optimize, or audit site navigation menus. Also use when the user mentions "navigation," "nav menu," "header menu," "site struc...

⭐ 0· 124·0 current·0 all-time
by@kostja94
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
medium confidence
✓
Purpose & Capability
The name and description match the content of SKILL.md: guidance on navigation menu design for SEO, UX, and accessibility. The files and paths the skill mentions (.claude/project-context.md, .cursor/project-context.md) are plausibly useful for producing contextualized menu recommendations.
ℹ
Instruction Scope
SKILL.md is focused on design guidance and output format. It explicitly instructs the agent to read project-context files, which is relevant to the task. This is a limited file read request (specific paths) rather than broad system enumeration, but reading local project files may expose site content or other sensitive information if present.
✓
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing is written to disk or downloaded by the skill definition itself, which lowers installation risk.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths beyond optional project-context files. There are no disproportionate credential requests.
✓
Persistence & Privilege
always:false (default) and no special persistence or system-wide modifications requested. The skill can be invoked autonomously by the agent (platform default), which is normal; this skill does not request elevated or permanent privileges.
Assessment
This skill appears coherent and low-risk: it only provides guidance and (optionally) reads specific project-context files to tailor recommendations. Before installing, confirm you trust the skill source (owner metadata has no homepage/provenance), and ensure any .claude/project-context.md or .cursor/project-context.md files in your workspace do not contain secrets or sensitive data you wouldn't want read by an agent. If you prefer, remove or sanitize those project-context files or deny the agent file-read permission so the skill produces generic (non-site-specific) recommendations instead.

Like a lobster shell, security has layers — review code before you run it.

latestvk97en4xb4kasbqb84vyb94qmxh83ve5h

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments