Trust Assessment
bird received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Obfuscated execution: base64 decode to shell, Remote Code Execution via Obfuscated MacOS Installation Script, Suspicious Windows Driver Download Source.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 | Obfuscated execution: base64 decode to shell Detected base64-encoded data being decoded and piped to a shell interpreter. This is a common obfuscation technique. Decode and inspect the base64 content before execution. | Static | skills/zaycv/blrd/SKILL.md:10 | |
| CRITICAL | Remote Code Execution via Obfuscated MacOS Installation Script The MacOS installation instructions include a base64-encoded command that, when decoded, downloads and executes a shell script from an arbitrary IP address (`http://91.92.242.30/6wioz8285kcbax6v`) using `curl | bash`. This allows for arbitrary remote code execution on the user's machine during skill installation, posing an extreme security risk. The IP address is not a trusted software distribution source, and the use of `base64 -D | bash` is a common technique for hidden instructions and malicious code execution. Remove the `base64 -D | bash` command. Provide a clear, auditable, and secure installation method, preferably through a package manager or by linking to a signed executable from a trusted domain. If a script must be executed, it should be hosted on a trusted domain, its contents should be auditable, and users should be instructed to review it before execution. | LLM | SKILL.md:14 | |
| HIGH | Suspicious Windows Driver Download Source The Windows installation instructions direct users to download an executable driver from a GitHub repository named `toolitletolate/openclaw_windriver`. While GitHub itself is a legitimate platform, the repository name is unusual and the direct download of an executable from a potentially untrusted or less-vetted source introduces a significant supply chain risk. The archive also requires a password (`openclaw`), which adds a layer of obscurity without necessarily increasing security. Provide a more reputable and auditable source for the Windows driver. Ideally, the driver should be signed by a trusted certificate authority. If hosted on GitHub, ensure the repository is well-maintained, has a clear history, and is associated with a known entity. Consider providing checksums for downloaded files. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/cd0cb0534aea89e8)
Powered by SkillShield