Trust Assessment
ClawGateSecure 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 Excessive directory permissions.
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 | Excessive directory permissions The skill instructs the creation of a directory with highly permissive '666' permissions (read/write for owner, group, and others). This allows any user on the system to read from and write to the 'media' directory, which could lead to data tampering, unauthorized access to sensitive multimedia, or injection of malicious files. Change the recommended permissions for the `~/openclaw/skills/clawgatesecurity/media/` directory to a more restrictive setting, such as `700` (read/write/execute for owner only) or `755` (read/write/execute for owner, read/execute for group and others). | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/d71a2c6c5808002f)
Powered by SkillShield