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 Arbitrary Code Execution via Untrusted Script Source (macOS), Untrusted Binary Download for `openclaw-agent` (Windows), Implicit Excessive Permissions for Untrusted `openclaw-agent`.
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 | Arbitrary Code Execution via Untrusted Script Source (macOS) The skill instructs macOS users to copy and paste an installation script from `glot.io` into their terminal. `glot.io` is a pastebin-like service and not a trusted software distribution platform. Executing arbitrary code from an untrusted external source poses a critical command injection and supply chain risk, as the script's content is unknown and could perform malicious actions on the user's system. Do not instruct users to copy-paste and execute scripts from untrusted pastebin-like services. Provide a verifiable, signed installer or a script from a trusted, version-controlled source (e.g., a specific commit/tag on GitHub) with clear instructions on how to review its contents. | LLM | SKILL.md:19 | |
| HIGH | Untrusted Binary Download for `openclaw-agent` (Windows) The skill instructs Windows users to download and run an executable binary (`openclaw-agent`) from a specific GitHub user's release page (`hedefbari`). Downloading and executing binaries from arbitrary third-party sources without further verification (e.g., checksums, official project links, code signing) introduces a significant supply chain risk. The binary could be malicious or compromised. The requirement to use a password (`openclaw`) for extraction is also unusual and adds to the suspicion. Provide a link to the official project repository for `openclaw-agent` with clear instructions on how to build from source or download officially signed and verified binaries. Avoid direct links to arbitrary user releases. Explain the purpose of the `openclaw` password or remove it if unnecessary. | LLM | SKILL.md:17 | |
| HIGH | Implicit Excessive Permissions for Untrusted `openclaw-agent` The skill states that the `openclaw-agent` utility is 'IMPORTANT' and required for 'Polymarket trading operations'. Given that this agent is distributed from untrusted sources (as identified in other findings), instructing users to install and run it implies granting it significant permissions and trust, especially for financial transactions. If the agent is malicious, it could exploit these implicit permissions to compromise user data or funds. Clearly document the `openclaw-agent`'s functionality, source code, and security implications. Ensure it is distributed from a trusted, verifiable source with proper security assurances. Users should be fully aware of the permissions and trust they are granting to this agent. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/858f5f50918d7dfa)
Powered by SkillShield