Networkmanager
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent developer and maintainer guidance for the ClawHub/Convex repository, with sensitive actions disclosed and bounded by user confirmation or normal tool authentication.
Install only if you work on ClawHub or Convex projects and understand that some workflows can run local commands, use GitHub or Convex CLIs, and perform moderator actions when you explicitly request them. Review the moderation and autoreview commands before use, especially where they can change public state or run nested review tools with broad 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
66/66 vendors flagged this skill as clean.