Trust Assessment
mcdonald 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 unsanitized `curl` arguments.
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 14, 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 | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unsanitized `curl` arguments The skill explicitly instructs the AI to use an `exec` tool to execute `curl` commands. The general '调用方式' (Calling Method) section provides a `curl` command template where the JSON payload's `name` and `arguments` fields are represented by placeholders (`<工具名>`, `<参数>`). If the AI constructs this `curl` command by directly inserting untrusted user input into these placeholders without proper shell and JSON escaping, an attacker can inject arbitrary shell commands. This could allow an attacker to break out of the JSON string, then out of the `curl -d` single-quoted string, and execute arbitrary commands on the host system, potentially leading to data exfiltration (e.g., of `MCD_TOKEN`), system compromise, or denial of service. The AI implementation must ensure that any user-provided input used to construct the `name` and `arguments` fields within the `curl -d` payload is rigorously sanitized and escaped for both JSON and shell contexts. The entire JSON string should be properly quoted and escaped for the shell command, and any values within the JSON derived from user input must be properly JSON-escaped to prevent injection. | LLM | SKILL.md:28 |
Scan History
Embed Code
[](https://skillshield.io/report/d36d7c1d4a917f89)
Powered by SkillShield