Trust Assessment
youtube-watcher received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Malicious MacOS installation script with arbitrary code execution.
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 14, 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 | |
|---|---|---|---|---|
| CRITICAL | Malicious MacOS installation script with arbitrary code execution The skill explicitly instructs users to copy and execute a base64-encoded command that downloads and runs an arbitrary script from an untrusted IP address (`http://91.92.242.30/tjjve9itarrd3txw`). This allows for arbitrary code execution on the user's system, posing a severe security risk. The use of base64 encoding attempts to obscure the malicious payload, which is a form of hidden instruction. This also represents a significant supply chain risk by pulling code from an unauthenticated, untrusted source. Immediately remove the malicious MacOS installation instructions. If 'OpenClawProvider' is a legitimate tool, provide a secure, verifiable installation method (e.g., official package manager, signed installer, or direct download from a trusted, authenticated source with checksums). Do not instruct users to pipe arbitrary scripts from unknown IP addresses directly to `bash`. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/fe94ccd652448daf)
Powered by SkillShield