Trust Assessment
youtube-summarize 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 Network egress to untrusted endpoints, Arbitrary Code Execution via Untrusted Script Source (macOS), Untrusted Executable Download from Personal GitHub Repository (Windows).
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 12, 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 | Network egress to untrusted endpoints URL pointing to known exfiltration/webhook service Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/hightower6eu/youtube-summarize-l4hjv/SKILL.md:10 | |
| CRITICAL | Arbitrary Code Execution via Untrusted Script Source (macOS) The skill instructs macOS users to download and execute an arbitrary script from `glot.io` (a public code-sharing service) by copying and pasting it into their terminal. This is a severe security risk, as the content of the script is untrusted and could contain malicious commands, leading to arbitrary code execution on the user's system. This instruction bypasses any security checks and relies entirely on the user's vigilance and the integrity of a third-party, ephemeral service. Remove the instruction to execute scripts from untrusted sources like `glot.io`. If `openclaw-agent` is a necessary dependency, provide a secure, verifiable installation method (e.g., official package manager, signed binaries from a trusted domain, or a clearly documented build process from a trusted source repository). | LLM | SKILL.md:9 | |
| HIGH | Untrusted Executable Download from Personal GitHub Repository (Windows) The skill instructs Windows users to download and run an executable (`openclaw-agent.zip`) from a personal GitHub repository (`hedefbari/openclaw-agent`) rather than an official or verified source. This introduces a significant supply chain risk, as the executable's integrity and trustworthiness cannot be guaranteed. Running unverified executables can lead to malware infection, system compromise, or other security breaches. The instruction to use a specific password (`openclaw`) for extraction also adds to the suspicious nature. Provide a secure and verifiable source for `openclaw-agent`. If it's an official OpenClaw component, host it under the official organization's releases. If it's a third-party tool, clearly identify it as such and provide appropriate warnings, or consider integrating a more trusted alternative. Avoid instructing users to download and run executables from unverified personal repositories. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/09660cad86ec7c1c)
Powered by SkillShield