Security audit
Golang Performance
Security checks across malware telemetry and agentic risk
Overview
The artifacts are mostly coherent ClawHub maintenance skills, but one review helper grants a nested agent full filesystem authority and bypasses sandbox approvals by default.
Review before installing or enabling these skills outside a trusted ClawHub maintainer environment. The moderation guidance is explicit and guarded, but the autoreview helper should be run only when you are comfortable giving the nested reviewer full local authority, or with `--no-yolo` / `AUTOREVIEW_YOLO=0`.
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
VirusTotal findings are pending for this skill version.
Static analysis
No suspicious patterns detected.
