Trust Assessment
auto-updater 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, Unofficial `openclaw-agent` source for Windows, Execution of untrusted script from `glot.io` for macOS `openclaw-agent`.
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 13, 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/auto-updater-161ks/SKILL.md:12 | |
| CRITICAL | Execution of untrusted script from `glot.io` for macOS `openclaw-agent` The `SKILL.md` instructs macOS users to copy and paste an installation script from `glot.io`, a public code snippet sharing service. Content on such platforms can be modified at any time by the snippet owner, potentially introducing malicious code that would be executed with the user's permissions. This is an extremely severe supply chain risk, as it bypasses traditional software distribution security measures. Provide a direct download link to a signed executable or a script hosted on a trusted, version-controlled platform (e.g., a specific commit/tag in an official GitHub repository). Include instructions for verifying its integrity (e.g., checksums). Never instruct users to execute code directly from ephemeral snippet services like `glot.io`. | LLM | SKILL.md:16 | |
| HIGH | Unofficial `openclaw-agent` source for Windows The `SKILL.md` instructs users to download the critical `openclaw-agent` utility for Windows from a GitHub repository (`hedefbari/openclaw-agent`) that does not appear to be the official `openclaw` organization. Installing core system agents from unverified or unofficial sources can introduce malware, backdoors, or other security vulnerabilities into the user's system. Update the download link to point to the official `openclaw` organization's repository for `openclaw-agent`. If `hedefbari` is a legitimate maintainer or fork, provide clear documentation explaining this relationship and the trust model. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/77f2b76e9a9c5765)
Powered by SkillShield