ui-taste
Verdict safe, but 1 finding (1 low), mainly obfuscation. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Give your coding agent better UI taste. Build and polish web and iOS interfaces with Uizze's anti-ui-slop playbooks and optional real-product references. Use for UI design, implementation, redesign, critique, or a final visual review in Claude Code, Codex, Cursor, or Copilot.
- Package
- 19 files, 116 KB
- SKILL.md
- 765 words, 8 sections
- Code
- None. Instructions only.
- License
- Apache-2.0; see LICENSE and NOTICE for third-party attribution
SKILL.md covers: UI Taste by Uizze · Prerequisites · Authentication · Work from the product · Image first, then implement · Select the workflow · Optional Uizze evidence · Finish
Findings
LOW Hidden data file detected Obfuscationstatic
Hidden file found: .wellknown-origin.json. Hidden files may contain concealed configuration or data that should be reviewed.
.wellknown-origin.json
What is in the package
| File | Kind | Size |
|---|---|---|
.wellknown-origin.json | config | 443 B |
CHECKSUMS.sha256 | other | 1.4 KB |
LICENSE | other | 11 KB |
MANIFEST.json | config | 7.8 KB |
MODIFICATIONS.md | doc | 2.5 KB |
NOTICE | other | 1.9 KB |
SKILL.md | doc | 6.0 KB |
agents/openai.yaml | config | 239 B |
reference/audit.md | doc | 8.8 KB |
reference/audit.native.md | doc | 11 KB |
reference/craft.md | doc | 8.8 KB |
reference/distill.md | doc | 1.1 KB |
reference/ios.md | doc | 4.5 KB |
reference/new-work.md | doc | 15 KB |
reference/operate.md | doc | 3.8 KB |
reference/overdrive.md | doc | 11 KB |
reference/polish.md | doc | 8.7 KB |
references/uizze-image-to-ui.md | doc | 10 KB |
references/uizze-reference-policy.md | doc | 2.2 KB |
External hosts referenced
github.com uizze.com developer.apple.com www.apache.org uizze.sh
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://uizze.sh/.well-known/skills/index.json
- Raw scan result: site-uizze.sh-ui-taste-scan.json
- Badge for your README:
- Request a re-scan