Trust Assessment
youtube-voice-summarizer received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 4 critical, 0 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Unpinned npm dependencies in backend setup.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, 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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address 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/franciscoandsam/youtube-voice-summarizer-elevenlabs/SKILL.md:42 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address 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/franciscoandsam/youtube-voice-summarizer-elevenlabs/SKILL.md:52 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address 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/franciscoandsam/youtube-voice-summarizer-elevenlabs/SKILL.md:92 | |
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address 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/franciscoandsam/youtube-voice-summarizer-elevenlabs/SKILL.md:105 | |
| MEDIUM | Unpinned npm dependencies in backend setup The skill's setup instructions for its required backend service (`elevenlabs-moltbot`) use `npm install`. Without a `package-lock.json` or using `npm ci`, this command can pull unpinned or latest versions of dependencies, which could introduce vulnerabilities or breaking changes if a dependency is compromised or updated maliciously. This creates a supply chain risk for the skill's operational environment. Ensure the `elevenlabs-moltbot` repository includes a `package-lock.json` file and instruct users to use `npm ci` instead of `npm install` for consistent and secure dependency installation. Regularly audit dependencies for known vulnerabilities. | LLM | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/e6781fcadb2b2def)
Powered by SkillShield