Github Trending
Security checks across malware telemetry and agentic risk
Overview
The skill appears to be a coherent ClawHub maintainer/developer workflow with powerful but disclosed commands that depend on user direction.
Install or use this only in a ClawHub maintainer/developer context. Review commands before running write actions, protect GitHub/Convex/ClawHub credentials, and use the safer autoreview opt-out if you do not want nested Codex 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
65/65 vendors flagged this skill as clean.