Security audit
02 Sleep Cry
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent maintainer/developer workflow skills, with disclosed command use and no evidence of hidden exfiltration or destructive behavior.
Install only in trusted ClawHub development or maintainer environments. Review the autoreview helper before use, especially its default full-access nested Codex mode, and use the documented no-yolo option if you want normal sandbox prompts. Treat moderation and PR publishing skills as privileged workflows that should only be run with the intended account and explicit target.
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
60/60 vendors flagged this skill as clean.