Security Audit
jnMetaCode/superpowers-zh:skills/using-git-worktrees
github.com/jnMetaCode/superpowers-zhTrust Assessment
jnMetaCode/superpowers-zh:skills/using-git-worktrees received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Unsanitized input used in shell commands.
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 March 25, 2026 (commit 03baa780). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unsanitized input used in shell commands The skill constructs shell commands using variables that are likely derived from user input or untrusted sources. Specifically, the `$BRANCH_NAME` variable, which is expected to be user-provided, is directly interpolated into a `git worktree add` command without apparent sanitization. A malicious user could inject arbitrary shell commands by providing specially crafted input for the branch name (e.g., `mybranch; rm -rf /`). This could lead to remote code execution on the host system. The `$path` variable, which also incorporates `$BRANCH_NAME`, is used in a `cd` command, posing a similar risk. Implement robust input validation and sanitization for all variables derived from user input or untrusted files (like `CLAUDE.md`) before they are used in shell commands. Specifically, ensure `$BRANCH_NAME` and any components of `$path` are strictly validated to contain only allowed characters (e.g., alphanumeric, hyphens, slashes) and are free of shell metacharacters. When executing shell commands, prefer using argument lists (e.g., `subprocess.run(['git', 'worktree', 'add', path, '-b', branch_name])` in Python) over single shell strings to prevent shell injection. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/682711e8106af7ba)
Powered by SkillShield