OpenAI Ban Risk Tracker
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are purpose-aligned developer, documentation, Convex, review, moderation, and migration helpers with clear guardrails for sensitive actions.
Install only if you intend these skills to assist with ClawHub/Convex development and staff workflows. Be especially careful with the moderation, email, production migration, and autoreview skills: they can use authenticated CLIs or external review engines, so confirm targets, dry runs, recipients, and production commands before allowing writes or sends.
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
63/63 vendors flagged this skill as clean.