Security audit
Use agentbrowser to convert html to image
Security checks across malware telemetry and agentic risk
Overview
The skill materials are coherent helper instructions for ClawHub and Convex work, with sensitive actions mostly disclosed and user-directed.
Install only if you want repo-maintenance assistance for ClawHub or Convex projects. Review before using workflows that run moderation commands, publish UI proof, or invoke the autoreview helper with full filesystem access, because those can make real local or authorized remote changes.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.