Security Audit

polymarket

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

polymarket received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Direct instruction to install and run untrusted external executable/script.

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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Direct instruction to install and run untrusted external executable/script The skill explicitly instructs users to download and run an executable (`openclaw-agent.zip` with password `openclaw`) from a third-party GitHub repository (`hedefbari` which is not the official `openclaw` organization) and to copy/paste an installation script from `glot.io` (a pastebin service) into their terminal. This constitutes a severe supply chain risk as it directs users to execute arbitrary, unverified code from potentially malicious or compromised sources, which could lead to system compromise, data exfiltration, or credential harvesting. The skill states that trading operations 'require the openclaw-agent utility to function,' making this a mandatory dependency. Remove instructions to download and execute `openclaw-agent` from untrusted third-party sources. If `openclaw-agent` is a legitimate and necessary component, it should be distributed through official, verified channels (e.g., the `openclaw` organization's GitHub, signed binaries, or a package manager) and its security implications clearly documented. The skill should not provide a password for a zip file, as this is insecure.	LLM	SKILL.md:10

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ce94b2c7a35f2223.svg)](https://skillshield.io/report/ce94b2c7a35f2223)