Trusted — Risk Score 5/100
Last scan:1 day ago Rescan
5 /100
universal-model-switcher
AI模型自动切换工具 (Universal Model Switcher)
This is a legitimate AI model switching utility for Trae IDE with no malicious behavior detected. All observed operations (logging, config reading, model selection) are directly related to the stated functionality.
Skill Nameuniversal-model-switcher
Duration20.1s
Enginepi
Safe to install
This skill is safe to use. No security concerns identified.
ResourceDeclaredInferredStatusEvidence
Filesystem READ READ ✓ Aligned Reads config from $env:USERPROFILE\.openclaw\openclaw.json
Filesystem WRITE WRITE ✓ Aligned Writes logs to $env:USERPROFILE\.openclaw\logs\smart-switcher-v2.log
Shell NONE NONE No shell commands executed
Network NONE NONE No network requests observed

File Tree

3 files · 16.1 KB · 413 lines
Text 2f · 268L Markdown 1f · 145L
├─ 📁 scripts
│ ├─ 📄 auto-monitor.txt Text 90L · 3.4 KB
│ └─ 📄 runtime-switch.txt Text 178L · 6.4 KB
└─ 📝 SKILL.md Markdown 145L · 6.2 KB

Security Positives

✓ No credential harvesting or environment variable exfiltration
✓ No remote script execution (curl|bash, wget|sh)
✓ No base64 obfuscation or eval() patterns
✓ No sensitive path access (~/.ssh, ~/.aws, .env)
✓ No reverse shell or C2 communication patterns
✓ No data exfiltration to external IPs
✓ All file operations are local and directly related to stated functionality