Trust Assessment
browser received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary Code Execution via `npm install`, Global Command Installation via `npm link`.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
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 | |
|---|---|---|---|---|
| CRITICAL | Arbitrary Code Execution via `npm install` The skill's setup instructions explicitly direct the agent to execute `npm install`. With the declared `Bash` permission, this command can download and execute arbitrary code defined in the `package.json` file (e.g., via `preinstall`, `postinstall` scripts) or within its dependencies. This creates a critical supply chain risk and allows for arbitrary code execution on the host system. Avoid instructing `npm install` directly. If dependencies are required, they should be pre-installed in a secure environment or the skill should run within a tightly sandboxed container. All dependencies must be thoroughly audited and pinned to specific versions. | LLM | SKILL.md:24 | |
| HIGH | Global Command Installation via `npm link` The skill's setup instructions direct the agent to execute `npm link`. With the declared `Bash` permission, this command creates a global symbolic link to the skill's executable, making it available system-wide. This can lead to unintended system modifications, potential command hijacking, or privilege escalation if the linked executable is malicious or conflicts with existing system commands. Avoid global installations. If a CLI tool is necessary, consider local execution within the skill's directory or a containerized environment to limit its scope and impact on the host system. | LLM | SKILL.md:25 |
Scan History
Embed Code
[](https://skillshield.io/report/ac3ac1d8d52d84d7)
Powered by SkillShield