Security audit
IceCube Monetize CN
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent development and moderation helpers with disclosed, user-directed commands and no evidence of hidden malicious behavior.
Install this only in a ClawHub or Convex development environment where you expect agents to use local authenticated tools. Before running moderation, PR publishing, proof, or full-access review helpers, verify the target account, command, and intended side effects.
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.