Security audit
World News API
Security checks across malware telemetry and agentic risk
Overview
The skills look mostly purpose-built for ClawHub and Convex work, but the autoreview helper grants a nested Codex review full local access by default.
Install only if you are comfortable with these skills using your local development tools and credentials for ClawHub/Convex workflows. Before using the autoreview helper, consider opting out of full-access mode with its documented no-yolo option, and review any GitHub, moderation, Convex deploy, or proof-publishing command before it runs.
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
60/60 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.