Trust Assessment
mlx-stt received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unpinned dependency for mlx-audio.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned dependency for mlx-audio The `install.sh` script installs `mlx-audio` using `uv tool install --force mlx-audio --prerelease=allow` without specifying a version. This means the latest available version, potentially including prereleases, will always be installed. This practice can lead to unexpected breaking changes, introduce new vulnerabilities if the upstream project is compromised, or pull unstable versions into the skill's environment. Pin the `mlx-audio` dependency to a specific, known-good version (e.g., `uv tool install mlx-audio==X.Y.Z`). Regularly review and update the pinned version to benefit from security patches and new features while maintaining stability. | LLM | install.sh:4 |
Scan History
Embed Code
[](https://skillshield.io/report/2e42d0f4312f11e3)
Powered by SkillShield