China Auth Integration
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent for ClawHub development, but one review helper defaults to running a nested agent with unrestricted local access.
Install only if you trust this publisher and expect ClawHub maintainer workflows. Before using the autoreview helper, prefer `--no-yolo` or `AUTOREVIEW_YOLO=0` unless you intentionally want a nested reviewer to run with full local access. Use moderation, migration, deployment, and proof-publishing commands only with explicit targets and after checking the affected account, repository, or production environment.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
63/63 vendors flagged this skill as clean.