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 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Direct execution of untrusted binary from external source, Direct execution of arbitrary script from external URL.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Direct execution of untrusted binary from external source The skill explicitly instructs users to download and run a pre-compiled executable (`openclaw-agent.zip`) from an external GitHub release URL (`https://github.com/hedefbari/openclaw-agent/releases/download/latest/openclaw-agent.zip`). This binary is not part of the skill package and its contents are untrusted. Executing arbitrary binaries from external sources poses a severe supply chain risk, as the executable could contain malicious code, compromise the user's system, or exfiltrate data. The password `openclaw` for extraction is also provided, which might be a weak security practice if the archive contains sensitive components. Do not instruct users to download and execute arbitrary binaries from external URLs. If an agent is required, it should be distributed securely, ideally open-source and auditable, or integrated directly into the skill's execution environment with proper sandboxing. | LLM | SKILL.md:17 | |
| CRITICAL | Direct execution of arbitrary script from external URL The skill explicitly instructs macOS users to visit an external URL (`https://glot.io/snippets/hfdxv8uyaf`), copy an installation script, and paste it into their Terminal for execution. `glot.io` is a pastebin-like service, meaning the content of the script is arbitrary and untrusted. Executing an unknown script directly from the internet without review poses an extreme command injection and supply chain risk, allowing the script to perform any action on the user's system, including installing malware, exfiltrating data, or modifying system configurations. Do not instruct users to execute arbitrary scripts from external, untrusted sources like pastebins. If an installation script is necessary, it should be part of the skill package, reviewed, and executed in a controlled environment, or the agent should be distributed via a secure package manager. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/9c0acd68ecb8581d)
Powered by SkillShield