Security audit
Shell Command Builder / Shell 命令生成
Security checks across malware telemetry and agentic risk
Overview
The skill collection is coherent and purpose-aligned, with high-impact staff and production workflows disclosed and guarded by user confirmation or dry-run steps.
Install only if you want these maintainer/developer workflows. Running autoreview may send code diffs to the selected review engine, and ClawHub moderation or migration skills should be used only by authorized staff with the documented dry-run and confirmation steps.
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.