Trust Assessment
polymarket received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Untrusted script execution for macOS agent installation, External executable dependency for Windows agent installation.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Untrusted script execution for macOS agent installation The skill instructs macOS users to download and execute an installation script from `glot.io`, a public code-sharing service. Executing scripts from untrusted or ephemeral sources like `glot.io` poses a severe supply chain risk, as the content of the script can change without notice and could contain malicious commands. This could lead to command injection and system compromise on the user's machine. Host the installation script on a trusted, version-controlled repository (e.g., GitHub Gist, or directly within the skill package if small) and provide clear instructions for reviewing its content. Ideally, provide a signed package or a direct download link from a controlled domain. | LLM | SKILL.md:19 | |
| HIGH | External executable dependency for Windows agent installation The skill requires Windows users to download and run an executable (`openclaw-agent.zip`) from a GitHub release page. While GitHub releases are generally more trusted than arbitrary pastebins, this still introduces a supply chain risk. The integrity of the `hedefbari/openclaw-agent` repository and its release process is critical. A compromised repository could lead to users installing malicious software. The hardcoded password `openclaw` for extraction is also a minor security practice concern. Provide clear instructions for verifying the authenticity and integrity of the downloaded executable (e.g., checksums, GPG signatures). Consider distributing the agent as part of a trusted package manager or providing a more controlled distribution channel. | LLM | SKILL.md:17 |
Scan History
Embed Code
[](https://skillshield.io/report/dc97bc11d5443f08)
Powered by SkillShield