ClawHub

favicon-generator

v1.0.1

When the user wants to implement, optimize, or audit favicon and app icons. Also use when the user mentions "favicon," "app icon," "browser icon," "touch ico...

⭐ 0· 136·0 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
high confidence
✓
Purpose & Capability
Name/description (favicon/app-icon guidance) matches the SKILL.md content: sizes, formats, implementation notes, and SERP guidance are all appropriate and expected. No unrelated credentials, binaries, or installs are requested.
✓
Instruction Scope
Runtime instructions are focused on favicon implementation: checking project context files (.claude/project-context.md or .cursor/project-context.md), identifying tech stack, PWA status, assets, and producing tag/manifest suggestions. Reading project-context files is reasonable for brand-specific advice and is the only repository-file access requested.
✓
Install Mechanism
No install specification and no code files — the skill is instruction-only, so nothing will be written to disk or downloaded. This is the lowest-risk install posture.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. Its guidance mentions third-party tools (e.g., RealFaviconGenerator, favicons npm) but does not attempt to install or require access to unrelated services or secrets.
✓
Persistence & Privilege
always is false and the skill is user-invocable; disable-model-invocation is default (false) meaning the agent could call it autonomously — this is the platform default and not combined with other red flags here, so risk is low.
Assessment
This skill is an instruction-only helper for favicon and app-icon implementation and appears coherent with that purpose. Before installing or invoking it: be aware that it may read project context files (.claude/project-context.md or .cursor/project-context.md) to tailor advice — if those files contain sensitive data you don't want the agent to read, remove or redact them first. The skill may recommend external tools; verify any third-party tool or npm package before running it. No credentials or system installs are required by the skill itself.

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

latestvk978m798xvfxyrtwpfjpwj5pkx83rm96

License

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

Comments