Trust Assessment
audit-website 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, 0 high, 1 medium, and 0 low severity. Key findings include Unsanitized user input in shell command, Unpinned external CLI dependency.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, 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 | Unsanitized user input in shell command The skill explicitly instructs the LLM agent to obtain a website URL from the user and then use it in `squirrel audit` shell commands. Without proper sanitization or quoting of this user-provided URL, a malicious user could inject shell metacharacters (e.g., `;`, `&&`, `|`) into the URL, leading to arbitrary command execution on the host system. The `allowed-tools` manifest permits `Bash(squirrel:*)`, but this does not mitigate command injection if arguments are not safely handled. Implement robust input sanitization and shell quoting for all user-provided inputs (especially URLs) before constructing and executing shell commands. When using `Bash` tools, ensure arguments are passed in a way that prevents shell interpretation of special characters, for example, by using `shlex.quote()` if constructing a single string command, or by passing arguments as a list to `subprocess.run` in Python. | LLM | SKILL.md:130 | |
| MEDIUM | Unpinned external CLI dependency The skill relies on the `squirrel` CLI tool, instructing users to install it from `squirrelscan.com/download`, but does not specify a required version. This creates a supply chain risk, as future versions of the `squirrel` CLI could introduce breaking changes, vulnerabilities, or malicious behavior that would affect the skill's operation or security without the agent's awareness or control. Specify a minimum or exact version for the `squirrel` CLI tool that the skill is compatible with. Instruct the user to install that specific version, or add a check within the skill to verify the installed `squirrel` version against a known compatible version. | LLM | SKILL.md:111 |
Scan History
Embed Code
[](https://skillshield.io/report/542259ab1b8dd5d7)
Powered by SkillShield