Novel Writer Skill
Security checks across malware telemetry and agentic risk
Overview
The skill bundle appears to provide disclosed ClawHub and Convex development workflows, with no artifact-backed evidence of hidden or malicious behavior.
Install this only in environments where ClawHub or Convex maintainer automation is appropriate. Review commands before running moderation or autoreview workflows, use the provided opt-out for full-access review mode if needed, and keep GitHub/Convex credentials scoped to the work being performed.
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.