Trust Assessment
openclaw-server-secure-skill 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 6 findings: 3 critical, 3 high, 0 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, 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 Findings6
| 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/kime541200/openclaw-server-secure-skill/SKILL.md:44 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/kime541200/openclaw-server-secure-skill/SKILL.md:53 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/kime541200/openclaw-server-secure-skill/SKILL.md:53 | |
| 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/kime541200/openclaw-server-secure-skill/SKILL.md:44 | |
| HIGH | Unverified remote script execution for Tailscale installation The skill uses `curl -fsSL https://tailscale.com/install.sh | sh` to install Tailscale. This method executes a script downloaded directly from the internet without local review or cryptographic verification via a package manager. A compromise of the `tailscale.com` server or a man-in-the-middle attack could lead to arbitrary code execution on the host system. Prefer installing software from official package repositories (e.g., `apt`, `yum`, `dnf`) which provide cryptographic verification. If a script must be used, download it, review its contents, verify its checksum/signature if available, and then execute it. | LLM | SKILL.md:47 | |
| HIGH | Global npm package installation without version pinning or integrity checks The skill uses `npm install -g openclaw` to install the OpenClaw agent globally. This command can execute arbitrary code via post-install scripts defined in the `openclaw` package or its dependencies. Without version pinning, it installs the latest version, which could introduce breaking changes or malicious code if the package is compromised. It relies solely on the integrity of the npm registry and the package maintainers. Pin the exact version of the `openclaw` package (e.g., `npm install -g openclaw@1.2.3`). Use `npm audit` regularly and consider using a `package-lock.json` or `npm shrinkwrap` for reproducible builds, even for global installations if possible, or a tool like `npx` for one-off executions. For critical system components, prefer containerization or more robust deployment methods. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/8e6a08c9e0101a08)
Powered by SkillShield