Trust Assessment
clawstarter received a trust score of 83/100, 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, 0 medium, and 1 low severity. Key findings include Node lockfile missing, Potential Command Injection via gh repo create.
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 | Potential Command Injection via gh repo create The skill's documentation suggests using the `gh repo create` command with placeholders `PROJECT_NAME` and `PROJECT_DESCRIPTION`. If an AI agent substitutes untrusted user input directly into these placeholders without proper sanitization or escaping, it could lead to command injection. This would allow an attacker to execute arbitrary shell commands on the host system by crafting malicious project names or descriptions. AI agents should implement robust input sanitization and escaping for any user-provided data before interpolating it into shell commands. For `gh repo create`, ensure that `PROJECT_NAME` and `PROJECT_DESCRIPTION` are properly quoted or validated to prevent shell metacharacters from being interpreted as commands. | LLM | SKILL.md:320 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/harrytou/clawstarter/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/6dd3393be4830e8c)
Powered by SkillShield