Trust Assessment
create-new-openclaw-in-gcp 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 18 findings: 8 critical, 6 high, 2 medium, and 2 low severity. Key findings include Covert behavior / concealment directives, Persistence / self-modification instructions, Arbitrary command execution.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings18
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:72 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:73 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:77 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:45 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:56 | |
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:34 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:44 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:56 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/id_ed25519'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:34 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:72 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:73 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:77 | |
| HIGH | Execution of unprovided external script The skill instructs the user to execute `openclaw-quick-setup.sh`. The content of this script is not provided within the analysis context. Executing unreviewed or externally sourced scripts poses a significant supply chain risk, as it could contain malicious commands or vulnerabilities that are not visible to the analyzer or the user. Include the full content of `openclaw-quick-setup.sh` within the skill package for review, or explicitly state its source and provide a hash for integrity verification if it must be downloaded. | LLM | SKILL.md:19 | |
| HIGH | Direct piping of external scripts to shell (curl | sh) The skill directly pipes scripts from external URLs (`https://tailscale.com/install.sh` and `https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh`) into `sh` or `bash`. This practice, often called 'curl | sh', is risky because it executes code from an external source without prior review or integrity verification. If the external server or the script's hosting platform were compromised, malicious code could be executed on the user's system. While the NVM script is version-pinned, its source is still external and executed without local review. The Tailscale script is not even version-pinned. Download these scripts, review their content, and include them locally within the skill package. Alternatively, verify their integrity using a checksum (e.g., `curl ... | sha256sum -c - && sh`) before execution. | LLM | SKILL.md:40 | |
| 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/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency The skill installs `openclaw` using `npm install -g openclaw@latest`. Using `@latest` means that any new version of the `openclaw` package will be installed, which could introduce breaking changes, vulnerabilities, or even malicious code if the package maintainer's account is compromised. Pinning to a specific version (e.g., `openclaw@1.2.3`) is a best practice for security and reproducibility. Pin the `openclaw` dependency to a specific, known-good version (e.g., `npm install -g openclaw@X.Y.Z`) to ensure consistent and secure installations. | LLM | SKILL.md:50 | |
| LOW | Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:10 | |
| LOW | Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/divide-by-0/create-new-openclaw-in-gcp/SKILL.md:11 |
Scan History
Embed Code
[](https://skillshield.io/report/ec3f4ebbb664758a)
Powered by SkillShield