Trust Assessment
kradleverse:init 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 Potential Command Injection in .env file creation, Potential Command Injection in `curl` arguments.
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 | Potential Command Injection in .env file creation The skill instructs the agent to write an API key and agent name to `~/.kradle/kradleverse/.env` using a `cat` command with a heredoc. If the values for `KRADLEVERSE_AGENT_NAME` or `KRADLEVERSE_API_KEY` are derived from untrusted user input and are not properly sanitized (e.g., for newlines or shell metacharacters), an attacker could inject arbitrary shell commands into the `.env` file. When this `.env` file is later sourced or processed by a shell, these injected commands would be executed. Ensure that any user-provided input used to populate `KRADLEVERSE_AGENT_NAME` or `KRADLEVERSE_API_KEY` is strictly sanitized to prevent shell metacharacters and newlines. Consider using a dedicated configuration management library or environment variable setting mechanism that handles escaping automatically, rather than direct shell redirection with potentially untrusted content. | LLM | SKILL.md:19 | |
| HIGH | Potential Command Injection in `curl` arguments The skill instructs the agent to construct `curl` commands using a `DESIRED_NAME` placeholder. If `DESIRED_NAME` is derived from untrusted user input and is not properly sanitized, an attacker could inject shell metacharacters (e.g., `;`, `&`, `|`, `$(...)`) to execute arbitrary commands on the system where the agent is running. This applies to both the URL query parameter and the JSON payload. All user-provided input used in shell commands, especially within URLs or JSON payloads, must be rigorously sanitized. For URL parameters, URL-encode the input. For JSON payloads, ensure the input is properly JSON-escaped. For the overall shell command, use proper quoting and escaping mechanisms (e.g., `printf %q` in bash) or pass arguments as separate parameters to the `curl` command if using a programming language wrapper, to prevent shell interpretation. | LLM | SKILL.md:11 |
Scan History
Embed Code
[](https://skillshield.io/report/5f285c6a74f5178d)
Powered by SkillShield