Trust Assessment
code-explain received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned `npx` dependency in usage examples, User code sent to external AI service.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned `npx` dependency in usage examples The skill's usage examples recommend executing `npx ai-explain` without specifying a version. This means the latest version of the `ai-explain` package will always be fetched and executed. This introduces a supply chain risk, as a malicious update to the `ai-explain` package could lead to arbitrary code execution on the system where `npx` is run. If an AI agent were to generate or recommend this command, it would propagate this insecure practice. Specify a version for the `ai-explain` package in all `npx` commands, e.g., `npx ai-explain@1.0.0 ./src/utils/crypto.ts`, or recommend installing it globally with a pinned version (`npm install -g ai-explain@1.0.0`). | LLM | SKILL.md:10 | |
| MEDIUM | User code sent to external AI service The skill describes a tool (`ai-explain`) that explicitly states `OPENAI_API_KEY required`. The tool's purpose is to explain user-provided code. This implies that any code provided by the user (via file paths or stdin) will be transmitted to OpenAI's servers for processing. This constitutes data exfiltration of potentially sensitive user code to a third-party service. While this is the intended functionality, users should be explicitly aware of this data handling practice. Clearly state in the skill's description that user-provided code will be transmitted to OpenAI's servers. Advise users not to provide sensitive or proprietary code if they are concerned about data privacy with third-party services. | LLM | SKILL.md:36 |
Scan History
Embed Code
[](https://skillshield.io/report/2815b827ebe9c61d)
Powered by SkillShield