Trust Assessment
lan-media-server 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 9 findings: 4 critical, 2 high, 3 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Network egress to untrusted endpoints, Sensitive environment variable access: $HOME.
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 Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/nagellack5c/lan-media-server/scripts/setup.sh:9 | |
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/nagellack5c/lan-media-server/scripts/setup.sh:46 | |
| 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/nagellack5c/lan-media-server/SKILL.md:38 | |
| 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/nagellack5c/lan-media-server/scripts/server.js:68 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/nagellack5c/lan-media-server/scripts/setup.sh:9 | |
| HIGH | Persistence mechanism: systemd service Detected systemd service pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/nagellack5c/lan-media-server/scripts/setup.sh:46 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nagellack5c/lan-media-server/SKILL.md:20 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/nagellack5c/lan-media-server/scripts/setup.sh:6 | |
| MEDIUM | Skill enables unauthenticated file sharing on LAN The skill's core functionality is to start an unauthenticated HTTP server on the local network (listening on `0.0.0.0`) to serve files from a designated directory (`MEDIA_ROOT`). While this is the intended purpose and the `SKILL.md` explicitly warns users not to place sensitive files in this directory, it inherently creates a mechanism for data exfiltration if the user misuses the skill or if sensitive data is inadvertently placed in the shared folder. Any device on the local network can access these files without authentication. Ensure users are fully aware of the security implications of placing sensitive data in the shared directory. The existing `SKILL.md` provides a good warning, but it is crucial that this warning is prominent and understood. Consider adding a runtime prompt or confirmation if the `MEDIA_ROOT` is changed to a potentially sensitive location. | LLM | scripts/server.js:58 |
Scan History
Embed Code
[](https://skillshield.io/report/d24c8bc1f385c1d5)
Powered by SkillShield