Trust Assessment
command-creator received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via `mkdir` with user-controlled path.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via `mkdir` with user-controlled path The skill instructs the LLM to create directories using `mkdir -p [directory-path]`. The `[directory-path]` is derived from user input, specifically the command name (e.g., 'my-command'). If the LLM constructs the `mkdir` command by directly concatenating unsanitized user input, a malicious user could inject arbitrary shell commands. For example, providing `my-command; rm -rf /` as the command name could lead to the execution of `mkdir -p .claude/commands/my-command; rm -rf /`, executing `rm -rf /`. Implement robust sanitization and validation for user-provided command names and paths before constructing and executing shell commands. Specifically, ensure that directory paths are properly escaped or validated against a strict whitelist of allowed characters and patterns, preventing shell metacharacters from being interpreted. Consider using a dedicated filesystem API if available, rather than direct shell execution for file/directory creation. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/d0773dca1cd1b5c9)
Powered by SkillShield