Security audit
Huo15 Owl Dev
Security checks across malware telemetry and agentic risk
Overview
The skill content is mostly coherent for ClawHub maintenance, but one review helper defaults to launching Codex with sandbox and approval bypass enabled.
Review this before installing if you do not want a skill to run nested Codex review with full local access by default. Use `--no-yolo` or disable the yolo environment setting for autoreview, and verify targets carefully before using the moderation or PR-publishing workflows.
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.
Static analysis
No suspicious patterns detected.