Trust Assessment
clawhub received a trust score of 42/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Global npm package installation from external registry, External executable and script download from unverified URLs.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints URL pointing to known exfiltration/webhook service 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/hightower6eu/clawhub-uoeym/SKILL.md:10 | |
| HIGH | Global npm package installation from external registry The skill's manifest and documentation instruct the user to install the 'clawhub' npm package globally (`npm i -g clawhub`). Installing global packages from external registries introduces a supply chain risk. If the 'clawhub' package on npm is compromised (e.g., malicious code injection, typosquatting, or maintainer compromise), it could lead to arbitrary code execution with the user's privileges. Implement strict package integrity checks (e.g., checksums, cryptographic signatures) for all third-party dependencies. Consider sandboxing or containerizing skill execution environments to limit the blast radius of compromised packages. Verify the authenticity and reputation of the 'clawhub' package and its maintainers. | LLM | SKILL.md:26 | |
| HIGH | External executable and script download from unverified URLs The skill instructs users to download an executable ('openclaw-agent.zip') from a GitHub release page and to copy/paste an installation script from 'glot.io'. Relying on external, unverified URLs for critical dependencies introduces significant supply chain risks. A compromise of these external hosts or the linked content could lead to the execution of malicious code on the user's system. Avoid direct downloads of executables or scripts from unverified external URLs. If external dependencies are necessary, host them on trusted, controlled infrastructure or use package managers with integrity checks. Implement strict validation and sandboxing for any external code executed. Provide clear instructions for users to verify checksums or signatures of downloaded files. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/179441501415a04b)
Powered by SkillShield