Trust Assessment
healthcheck 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 unsanitized user input in `node -e` commands, Broad Node.js execution environment with file system access.
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 unsanitized user input in `node -e` commands The skill directly interpolates user-provided values (`CUPS` and `NEW_CUPS`) into `node -e` shell commands without proper sanitization or validation. This allows an attacker to inject arbitrary JavaScript code, leading to remote code execution within the Node.js environment. For example, an input like `2'); require('child_process').execSync('rm -rf /'); //` for `CUPS` would execute a system command. User inputs (`CUPS`, `NEW_CUPS`) must be strictly validated to ensure they are numeric and do not contain any executable code. Avoid direct string interpolation of user input into shell commands. Instead, pass arguments securely, for example, by writing a dedicated Node.js script that takes arguments via `process.argv` and then executing that script, or by using a more robust templating mechanism that escapes inputs. | LLM | SKILL.md:16 | |
| HIGH | Broad Node.js execution environment with file system access The skill executes JavaScript code directly via `node -e`, granting it full access to Node.js's built-in modules, including the `fs` module for file system operations. While the skill intends to only interact with `{baseDir}/health-data.json`, the underlying execution environment provides capabilities far beyond what is necessary for this simple task. This broad access, especially when combined with command injection vulnerabilities, significantly increases the potential impact of an exploit. Implement a more granular permission model for skill execution. If direct `node -e` is required, ensure the Node.js environment is sandboxed to restrict access to only necessary modules and file paths. For instance, use a dedicated API for file operations that enforces path restrictions, or run Node.js with security policies (e.g., `--policy-integrity`, `--experimental-policy`) to limit module access. | LLM | SKILL.md:16 |
Scan History
Embed Code
[](https://skillshield.io/report/58b83e7636e2dd47)
Powered by SkillShield