Trust Assessment
using-neon received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via unvalidated `curl` path.
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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unvalidated `curl` path The skill provides `curl` commands for fetching documentation. The command `curl -H "Accept: text/markdown" https://neon.com/docs/<path>` uses a placeholder `<path>`. If the AI agent executes this command and the `<path>` variable is not strictly validated and sanitized against shell metacharacters, a malicious user could craft a prompt to inject arbitrary shell commands (e.g., `https://neon.com/docs/foo; rm -rf /`) or exfiltrate local files (e.g., `https://neon.com/docs/$(cat /etc/passwd)`). Given the `claude_code` ecosystem, direct execution of such commands is a credible and severe threat. Implement strict input validation and sanitization for the `<path>` variable before constructing and executing the `curl` command. Ensure that only valid URL path characters are allowed and that no shell metacharacters can be injected. Ideally, use a dedicated, sandboxed tool execution environment or an API call instead of direct shell command execution for fetching external resources. If shell execution is unavoidable, use a library or function that safely escapes arguments for the shell. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/6956c6a01ccd7b2e)
Powered by SkillShield