Trust Assessment
openclaw-deploy 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 9 findings: 3 critical, 1 high, 5 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 42/100, 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 Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/zfanmy/openclaw-deploy/templates/install-node.sh:17 | |
| 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/zfanmy/openclaw-deploy/templates/install-node.sh:17 | |
| CRITICAL | Unsafe 'curl | bash' for NVM installation The 'install-node.sh' script uses 'curl ... | bash' to install NVM (Node Version Manager). This practice executes arbitrary code downloaded directly from the internet without prior review or validation. This poses a significant supply chain risk, as a compromise of the NVM GitHub repository or a man-in-the-middle attack could lead to arbitrary code execution on the user's system with the privileges of the script runner. Avoid piping remote scripts directly to a shell. Instead, download the script, review its contents, and then execute it locally. For NVM, consider using a package manager if available, or a more secure installation method that involves manual review. | LLM | templates/install-node.sh:16 | |
| HIGH | Sensitive configuration data copied into portable package The 'build-portable.sh' script copies the entire content of the user's OpenClaw configuration directory (defaulting to '/home/$(whoami)/.openclaw') into the 'full' portable package. This directory can contain sensitive user data, application settings, and potentially credentials or personal information. Packaging this data into a distributable archive creates a high risk of data exfiltration if the package is deployed to an untrusted environment, shared inappropriately, or falls into the wrong hands. Review the contents of the configuration directory and only include necessary, non-sensitive files in the 'full' portable package. Implement explicit filtering or sanitization of sensitive data before packaging. Clearly document the exact contents of the 'full' package and warn users about the sensitive nature of the included data. | LLM | scripts/build-portable.sh:80 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/zfanmy/openclaw-deploy/SKILL.md:1 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/zfanmy/openclaw-deploy/templates/install-node.sh:18 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/zfanmy/openclaw-deploy/templates/start-clean.sh:11 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/zfanmy/openclaw-deploy/templates/start-full.sh:11 | |
| MEDIUM | Generated remote deployment script with unverified content The 'export-portable.sh' script generates a 'deploy.sh' script and a 'README.md' file. The 'README.md' explicitly instructs users to execute the generated 'deploy.sh' for remote deployment (e.g., './deploy.sh user@remote-server clean /opt/openclaw'). The skill's requirements also list 'rsync', implying the generated script will perform high-privilege remote operations. Without access to the actual content of the generated 'deploy.sh', it's impossible to verify proper input sanitization or secure implementation, leading to potential command injection or excessive permissions on the remote server if arguments are not handled carefully. Provide the source code for the generated 'deploy.sh' script for security review. Ensure the generated script properly sanitizes all user-provided inputs (e.g., remote host, target path) to prevent command injection. Implement robust error handling and least-privilege principles for remote operations. | LLM | scripts/export-portable.sh:34 |
Scan History
Embed Code
[](https://skillshield.io/report/37a4a50093722ca0)
Powered by SkillShield