AI配音文案纠错
Security checks across malware telemetry and agentic risk
Overview
This appears to be a ClawHub maintainer/developer skill set, but one executable helper defaults to launching nested Codex with full sandbox bypass, which is broader than ordinary review work needs.
Install only if you trust the publisher and intend to use these ClawHub maintainer workflows. Before running autoreview, prefer the safer --no-yolo mode unless full local authority is explicitly needed, and use the moderation commands only with verified targets, reasons, and the expected authenticated staff account.
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.