Security audit
Poyo Xai Tts 1
Security checks across malware telemetry and agentic risk
Overview
The scanned artifacts appear to be legitimate ClawHub engineering and staff workflow skills with clear safeguards and no hidden malicious behavior found.
Install or enable these skills only in a ClawHub staff or development context. Review the moderation, content-rights, migration, and autoreview skills before use because they can send email, modify production state, or share code diffs with external review engines when explicitly invoked.
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.
Static analysis
No suspicious patterns detected.