Trust Assessment
command-creator received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 9 findings: 4 critical, 5 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Potential Command Injection via Unsanitized Shell Execution.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on August 1, 2026 (commit a4d31ad1). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | codex/command-creator/SKILL.md:8 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | codex/command-creator/SKILL.md:66 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | codex/command-creator/SKILL.md:68 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | codex/command-creator/SKILL.md:162 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | codex/command-creator/SKILL.md:8 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | codex/command-creator/SKILL.md:66 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | codex/command-creator/SKILL.md:68 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | codex/command-creator/SKILL.md:162 | |
| HIGH | Potential Command Injection via Unsanitized Shell Execution The skill instructs the agent to execute `mkdir -p [directory-path]` in the shell, where `[directory-path]` is derived from user-controlled input (the command name or user-specified location). If the user provides a command name containing shell metacharacters (e.g., `; malicious_command`), this can lead to arbitrary command execution on the host system. Instruct the agent to strictly validate the command name and directory path to ensure they only contain alphanumeric characters, hyphens, and slashes, and do not contain shell metacharacters or path traversal sequences (e.g., `..`) before executing any shell commands. | LLM | SKILL.md:145 |
Scan History
Embed Code
[](https://skillshield.io/report/1a6d51605e48b6ed)
Powered by SkillShield