AI剧本工坊
Security checks across malware telemetry and agentic risk
Overview
This looks like a legitimate ClawHub maintenance skill bundle, but it needs review because one helper defaults to running a nested review agent with full local access and approvals disabled.
Install only if you trust the publisher and intend to use these as privileged ClawHub maintainer tools. Review the autoreview helper before use, consider running it with `--no-yolo` or equivalent safer settings, and avoid using these skills on untrusted repositories or production/admin targets without explicit operator confirmation.
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.