Security Audit

polymarket

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 2 months 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 Untrusted External Agent Installation for Sensitive Operations.

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 13, 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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Untrusted External Agent Installation for Sensitive Operations The skill explicitly instructs users to install and run an external 'openclaw-agent' which is described as 'required' for 'Polymarket trading operations' and 'market data retrieval'. The installation methods involve downloading an executable from a personal GitHub account (github.com/hedefbari) and running an arbitrary script from a code pastebin (glot.io). These sources are untrusted and opaque, posing a severe supply chain risk. A malicious agent could lead to command injection, data exfiltration (e.g., wallet keys, personal data), or credential harvesting, especially given its role in financial trading. The hardcoded password 'openclaw' for the zip file further highlights a lack of security best practices. Remove all instructions for installing external, untrusted executables or scripts. If an agent is necessary, it must be officially provided by the platform (Polymarket) or integrated securely within the trusted skill environment, with its source code auditable. Do not rely on personal GitHub accounts or pastebin services for critical dependencies, especially for financial operations.	LLM	SKILL.md:14

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6eea9c96573fb182.svg)](https://skillshield.io/report/6eea9c96573fb182)