Ad Copy
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent, but the autoreview helper defaults to launching a nested Codex review with sandbox and approval bypass, which is unusually broad authority for a review tool.
Review this before installing if you are not comfortable with a skill that can invoke nested reviewer tools with full local access by default. For safer use, run the autoreview helper with `--no-yolo` or disable the helper, and only use the moderation and publish workflows from trusted ClawHub workspaces with the intended authenticated accounts.
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.