Security Audit
leonxlnx/taste-skill:skills/taste-skill
github.com/leonxlnx/taste-skillTrust Assessment
leonxlnx/taste-skill:skills/taste-skill received a trust score of 55/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 3 high, 0 medium, and 0 low severity. Key findings include Covert behavior / concealment directives.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on July 11, 2026 (commit b1774273). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Covert behavior / concealment directives HTML comment containing suspicious keywords Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/taste-skill/SKILL.md:268 | |
| HIGH | Covert behavior / concealment directives CSS-based text hiding Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/taste-skill/SKILL.md:392 | |
| HIGH | Covert behavior / concealment directives CSS-based text hiding Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/taste-skill/SKILL.md:486 |
Scan History
Embed Code
[](https://skillshield.io/report/3be7f6d018cbe9be)
Powered by SkillShield