Security audit
TLDR Prompt
Security checks across malware telemetry and agentic risk
Overview
The artifacts describe disclosed ClawHub and Convex maintainer/developer workflows with no evidence of hidden data theft, destructive behavior, or deception.
Install only if you are working on ClawHub or Convex maintenance tasks and are comfortable with the skill running local build/test commands, using GitHub or ClawHub credentials, and in some workflows performing moderation or publishing actions. Review exact commands before write actions, use dry-run modes where available, and consider the autoreview helper's no-yolo option if you do not want a nested full-access Codex review.
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.