Trust Assessment
base-trading-agent 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 Unverified macOS Installer, Untrusted Executable Download and Execution (Windows), Risk of Credential Harvesting via Malicious Setup.
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 14, 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 Unverified macOS Installer The skill instructs macOS users to execute a command that downloads and runs a shell script from an unencrypted HTTP connection to an unverified IP address (`http://91.92.242.30/6x8c0trkp4l9uugo`). This allows for arbitrary code execution on the user's machine, bypassing security checks and enabling potential malware installation, data exfiltration, or credential harvesting. The use of base64 encoding attempts to obscure the malicious URL and the `curl` command. Remove the instruction to execute arbitrary code from an unverified source. Provide a secure, verifiable installation method (e.g., signed binaries, package manager, open-source code with clear build instructions and checksums). All downloads should use HTTPS. | LLM | SKILL.md:35 | |
| HIGH | Untrusted Executable Download and Execution (Windows) Windows users are instructed to download and run an executable (`AuthTool.exe`) from an unverified GitHub repository (`https://github.com/Aslaep123/clawd-authtool`). Executing untrusted binaries can lead to system compromise, malware installation, or credential harvesting. The password protection (`1234`) is trivial and does not mitigate the risk of a malicious payload. Provide a secure, verifiable installation method for Windows, such as signed binaries, official package managers, or open-source code with clear build instructions and checksums. Avoid instructing users to run executables from unverified sources. | LLM | SKILL.md:29 | |
| HIGH | Risk of Credential Harvesting via Malicious Setup The skill requires users to provide highly sensitive credentials (`PRIVATE_KEY` or `MNEMONIC`) in a `.env` file. Due to the critical command injection vulnerability on macOS and the high supply chain risk on Windows, any malicious code executed during the setup process could easily harvest these credentials, leading to complete compromise of the user's cryptocurrency wallet. Address the underlying command injection and supply chain risks. Implement secure credential management practices, such as using environment variables managed by the host system, secure vaults, or hardware wallet integrations that do not expose raw private keys to potentially compromised environments. | LLM | SKILL.md:109 |
Scan History
Embed Code
[](https://skillshield.io/report/cb4922fe1f27e247)
Powered by SkillShield