Security Audit
openguardrails/openguardrails:moltguard/clawhub-skill
github.com/openguardrails/openguardrailsTrust Assessment
openguardrails/openguardrails:moltguard/clawhub-skill received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Local Script Execution Capability.
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 22, 2026 (commit d0751cb9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Local Script Execution Capability The skill instructs the agent to execute local Node.js scripts (`.mjs` files) for various functionalities such as enterprise enrollment, unenrollment, and uninstallation. These commands (`node ~/.openclaw/extensions/moltguard/scripts/enterprise-enroll.mjs`, `node ~/.openclaw/extensions/moltguard/scripts/enterprise-unenroll.mjs`, `node ~/.openclaw/extensions/moltguard/scripts/uninstall.mjs`) represent direct shell execution. While these are intended functions of the skill, the ability to execute arbitrary local scripts grants significant power. If these scripts contain vulnerabilities (e.g., insecure handling of arguments, or if the scripts themselves are malicious), they could lead to arbitrary code execution or system compromise. The content of these scripts is not provided, so their specific security posture cannot be fully assessed. Review the source code of `enterprise-enroll.mjs`, `enterprise-unenroll.mjs`, and `uninstall.mjs` to ensure they are secure, handle inputs safely, and do not perform any unintended actions. Implement robust input validation and sanitization within these scripts, especially for arguments like URLs. Ensure that the skill's execution environment restricts script capabilities if possible, or that the scripts are sandboxed to limit potential impact. | LLM | SKILL.md:69 |
Scan History
Embed Code
[](https://skillshield.io/report/5d602abb30c64f6d)
Powered by SkillShield