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 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Execution of unverified script from external pastebin (glot.io), Download and execution of unverified binary from third-party GitHub user, Reliance on external `openclaw-agent` with implied broad permissions for trading.
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 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 | Execution of unverified script from external pastebin (glot.io) The skill instructs users to visit `https://glot.io/snippets/hfdxv8uyaf`, copy an installation script, and paste it into their Terminal. Executing arbitrary scripts from an unverified external source like `glot.io` is a severe supply chain risk and a direct command injection vector. The content of the script is not provided or reviewed within the skill package, making it a black box that could contain malicious commands. Do not instruct users to execute scripts from unverified external pastebin services. If an installation script is necessary, it should be included directly within the skill package, signed, or hosted on a trusted, auditable domain controlled by the skill developer. Provide the script content for review. | LLM | SKILL.md:20 | |
| HIGH | Download and execution of unverified binary from third-party GitHub user The skill instructs users to download an executable (`openclaw-agent.zip`) from `https://github.com/hedefbari/openclaw-agent/releases/download/latest/openclaw-agent.zip`. The `hedefbari` GitHub user is not the `openclaw` organization, which is the apparent source of the skill. Downloading and executing binaries from an unverified third-party source introduces a significant supply chain risk, as the binary could be malicious or compromised. Host the `openclaw-agent` binary under the official `openclaw` GitHub organization or a trusted, auditable domain. Provide checksums for verification. Ideally, the agent should be open-source for community review. | LLM | SKILL.md:17 | |
| HIGH | Reliance on external `openclaw-agent` with implied broad permissions for trading The skill heavily relies on an external, closed-source `openclaw-agent` for 'trading operations' and 'API operations'. This agent is described as essential for interacting with Polymarket. Trading operations typically require access to user's wallet keys, API keys, or other sensitive credentials, implying broad permissions for the agent. Since the agent's source code is not provided or auditable within the skill context, users are asked to grant significant trust to an opaque executable, which poses a high risk for credential harvesting or unauthorized actions if the agent is compromised or malicious. Provide the source code for `openclaw-agent` for security review and auditing. Clearly document the exact permissions and access required by the agent and how it handles sensitive user data (e.g., private keys, API tokens). Implement secure methods for credential management (e.g., OS-level keyrings, secure enclaves) rather than relying on an opaque executable. | LLM | SKILL.md:14 |
Scan History
Embed Code
[](https://skillshield.io/report/63995f1bcf6eb024)
Powered by SkillShield