Publish Jira
Security checks across malware telemetry and agentic risk
Overview
This appears to be a disclosed ClawHub development and maintenance skill set with powerful commands, but the authority is purpose-aligned and generally user-directed.
Install or use this only if you are working on ClawHub or Convex maintenance and understand the authority involved. Review commands before running moderation, GitHub publishing/commenting, UI proof, or autoreview helpers, and use local or test credentials unless you intentionally need production 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.