Twist
Security checks across malware telemetry and agentic risk
Overview
The artifacts describe ClawHub and Convex workflow skills with powerful but disclosed, purpose-aligned commands and no evidence of hidden exfiltration or destructive behavior.
Install only if you want agents to help with ClawHub/Convex development and maintainer workflows. Review the moderation and autoreview skills carefully: moderation commands can affect users and public skills, and autoreview may send diffs to configured review tools and defaults to a full-access nested Codex review unless you opt out.
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.