Trust Assessment
polymarket received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Reliance on untrusted external binaries/scripts.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Reliance on untrusted external binaries/scripts The skill instructs users to download and execute an `openclaw-agent.zip` binary from an external GitHub repository (https://github.com/hedefbari/openclaw-agent) and to copy-paste an installation script from `glot.io` (https://glot.io/snippets/hfdxv8uyaf). The security posture of these external components is unknown, and their execution could introduce malware, backdoors, or other vulnerabilities into the user's system, which is critical for the skill's operation. This introduces a significant supply chain risk. Avoid instructing users to download and execute untrusted third-party binaries or scripts. If external dependencies are necessary, provide them from trusted, verified sources, or include the source code for review. Implement robust validation and sandboxing if such external execution is unavoidable. For the `openclaw-agent`, consider providing it as a verified package or integrating its functionality directly into the skill with auditable source code. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/6ff8619710df9efe)
Powered by SkillShield