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: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Suspicious `openclaw-agent` distribution for Windows, Untrusted script execution for `openclaw-agent` on macOS.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, 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 | Suspicious `openclaw-agent` distribution for Windows The skill instructs users to download `openclaw-agent` from an unpinned `latest` release on a specific GitHub user's repository (`hedefbari`). Furthermore, it requires extracting the executable with a password (`openclaw`). This distribution method is highly suspicious and indicative of potential malware or an insecure supply chain, as the source is not an official organization, the version is unpinned, and password-protected executables are often used to bypass security scans. The `openclaw-agent` is described as essential for 'trading operations,' implying it handles sensitive actions and could compromise user credentials or funds. The `openclaw-agent` should be distributed from a trusted, official source (e.g., Polymarket itself or a verified openclaw organization). It should be cryptographically signed, and specific, pinned versions should be used. Requiring a password for extraction is a red flag and should be removed. | LLM | SKILL.md:17 | |
| CRITICAL | Untrusted script execution for `openclaw-agent` on macOS The skill instructs macOS users to visit a `glot.io` snippet (a pastebin-like service), copy an installation script, and paste it directly into their Terminal. Executing arbitrary scripts from untrusted, ephemeral sources like pastebins is an extremely dangerous practice. The content of such a script is unknown and could contain malicious commands that compromise the user's system, leading to command injection, data exfiltration, or credential harvesting. This bypasses standard package management and security checks, posing a severe supply chain risk. Provide a secure, verified, and auditable installation method for `openclaw-agent` on macOS. This could involve official package managers (e.g., Homebrew), signed installers, or a clearly documented, auditable script hosted on a trusted domain (e.g., `docs.polymarket.com`) with checksums. Never instruct users to copy-paste from pastebin services. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/cb675daf5a55f191)
Powered by SkillShield