Security audit
Billons Ai
Security checks across malware telemetry and agentic risk
Overview
The available artifacts look like disclosed developer workflow skills, with no evidence of hidden data theft, destructive installation, or deceptive behavior.
Install only if you need these ClawHub or Convex maintainer workflows and understand the local and remote authority they may use. Review commands before running staff moderation actions, keep credentials limited to the intended ClawHub environment, and use the autoreview no-yolo option if you do not want nested review commands to run with full local access.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.