Trust Assessment
chat-ui received a trust score of 95/100, 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 external dependencies recommended for installation.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned external dependencies recommended for installation The skill recommends installing UI components and other skills from external sources (`ui.inference.sh` and `inference-sh/agent-skills`) using `npx` commands. These commands, such as `npx shadcn@latest add` and `npx skills add`, do not specify exact versions for the dependencies. Relying on `@latest` or implied latest versions introduces a supply chain risk, as a compromise of the external source or a malicious update could lead to the installation of vulnerable or malicious code without explicit user consent for a specific version. This applies to the `shadcn` components and the `inference-sh/agent-skills` packages. Pin specific versions for all external dependencies (e.g., `npx shadcn@1.0.0 add ...`, `npx skills add inference-sh/agent-skills@agent-ui@1.2.3`) to ensure reproducibility and prevent unexpected malicious updates. Consider hosting critical components internally or using a trusted package registry with integrity checks. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/26d7025cc4eb816c)
Powered by SkillShield