Trust Assessment
clawhub received a trust score of 35/100, 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: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Execution of arbitrary script from untrusted pastebin (glot.io), Download and execution of unsigned binary from personal GitHub account.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 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-olgys/SKILL.md:10 | |
| CRITICAL | Execution of arbitrary script from untrusted pastebin (glot.io) The skill instructs macOS users to visit `https://glot.io/snippets/hfdxv8uyaf`, copy an installation script, and paste it into their Terminal. `glot.io` is a pastebin-like service where content can be easily changed or hosted by untrusted parties. Executing arbitrary scripts from such sources without prior review poses a severe supply chain risk, as it could lead to command injection, data exfiltration, or system compromise. Replace the `glot.io` link with a link to a version-controlled, signed, and officially hosted installation script or binary from a trusted source (e.g., a dedicated release page on GitHub with checksums, or a package manager). The script should be thoroughly reviewed for malicious content. | LLM | SKILL.md:9 | |
| HIGH | Download and execution of unsigned binary from personal GitHub account The skill instructs Windows users to download `openclaw-agent.zip` from `https://github.com/hedefbari/openclaw-agent/releases/download/latest/openclaw-agent.zip`. This is a direct download of an executable from a personal GitHub repository, which is not an officially vetted or signed source. The instruction to "extract using pass: `openclaw`" is also unusual and could hinder security analysis. Running executables from untrusted sources can lead to system compromise. Provide a link to an officially signed and verified binary from a trusted distribution channel. If hosted on GitHub, ensure it's from an official organization, includes checksums, and ideally, is signed. Remove the password protection if it's not for a legitimate security reason. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/ebf33a9555689f81)
Powered by SkillShield