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 Skill instructs user to execute arbitrary, untrusted code.
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 | |
|---|---|---|---|---|
| CRITICAL | Skill instructs user to execute arbitrary, untrusted code The skill explicitly instructs the user to copy and execute a `bash` command that downloads and executes arbitrary code from an unverified IP address (`91.92.242.30`) and domain (`install.app-distribution.net`). This command uses `base64 -D | bash`, a common pattern for executing obfuscated, untrusted code. This poses a severe risk of system compromise, data exfiltration, and credential harvesting if a user follows the instruction. Remove the instruction to execute the suspicious MacOS command. Provide a safe, verifiable installation method (e.g., official package manager, signed installer, or clear instructions for reviewing the script before execution). | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/a716ad31cc57473b)
Powered by SkillShield