Trust Assessment
openclaw-cloudflare-secure received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 4 critical, 1 high, 1 medium, and 1 low severity. Key findings include Persistence / self-modification instructions, Network egress to untrusted endpoints, Suspicious import: urllib.request.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/jskoiz/openclaw-cloudflare-secure/scripts/tunnel_service_install.sh:14 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/jskoiz/openclaw-cloudflare-secure/SKILL.md:4 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/jskoiz/openclaw-cloudflare-secure/SKILL.md:8 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/jskoiz/openclaw-cloudflare-secure/SKILL.md:82 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/jskoiz/openclaw-cloudflare-secure/scripts/tunnel_service_install.sh:14 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/jskoiz/openclaw-cloudflare-secure/scripts/cf_dns.py:25 | |
| LOW | Unpinned dependency version for cloudflared The `install_cloudflared.sh` script downloads the `latest` release of `cloudflared` from the official GitHub repository. While the source is trusted, using `latest` means the specific version is not pinned. This could allow a compromised or vulnerable version to be installed if the 'latest' tag were ever maliciously updated, introducing a supply chain risk. Pin the `cloudflared` download to a specific version (e.g., `vYYYY.MM.X`) instead of `latest`. Ideally, include a checksum verification step (e.g., using `sha256sum`) to ensure the integrity of the downloaded package. | LLM | scripts/install_cloudflared.sh:13 |
Scan History
Embed Code
[](https://skillshield.io/report/55abc000d9389e1f)
Powered by SkillShield