习惯追踪器
Security checks across malware telemetry and agentic risk
Overview
The skill set is coherent for ClawHub and Convex maintenance workflows, with disclosed but powerful local and service-side actions users should run deliberately.
Install only if you want an agent to help with ClawHub/Convex maintenance. Review the autoreview helper before use, especially its default full-access nested Codex mode; use --no-yolo or disable auto tests if you want tighter local containment. Treat moderation, GitHub publishing, Convex deploy/dev, and migration commands as live-impact operations and confirm targets before running them.
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
66/66 vendors flagged this skill as clean.