Trust Assessment
kradleverse:init received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Direct Shell Command Execution with User-Controlled Input, Instruction to Store API Key in Local File.
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 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 | |
|---|---|---|---|---|
| HIGH | Direct Shell Command Execution with User-Controlled Input The skill explicitly instructs the agent to execute shell commands (`curl`). Placeholders like `DESIRED_NAME` are expected to be filled by the agent, potentially with user-provided input. If this input is not rigorously sanitized before being interpolated into the shell command, an attacker could inject arbitrary shell commands (e.g., `name=foo%26%26rm%20-rf%20/`), leading to remote code execution or other malicious activities. Implement robust input validation and sanitization for all user-provided inputs before they are used in shell commands. Avoid direct execution of shell commands with interpolated user input. Consider using safer API calls or libraries that handle command construction securely. If shell execution is unavoidable, use a sandboxed environment or strictly whitelist allowed commands and arguments. | LLM | SKILL.md:10 | |
| MEDIUM | Instruction to Store API Key in Local File The skill instructs the agent to store sensitive credentials (`KRADLEVERSE_AGENT_NAME` and `KRADLEVERSE_API_KEY`) in a local `.env` file (`~/.kradle/kradleverse/.env`) using a `cat` command. While this is a common practice for storing environment variables, it involves handling sensitive API keys in a plain-text file. If the agent's environment is compromised, the file permissions are insecure, or the agent inadvertently exposes the file, these credentials could be exposed. Ensure that the `.env` file is created with appropriate restrictive file permissions (e.g., `chmod 600`). Advise the agent to use secure credential storage mechanisms provided by the operating system or platform (e.g., secret managers, keychains) instead of plain text files where possible. Emphasize that the API key should be treated as highly sensitive and never hardcoded or exposed in logs. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/7d00dbcc4765ff83)
Powered by SkillShield