Security audit
Step3-VL Finetune
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and maintainer workflows with sensitive actions disclosed and generally gated by user intent or confirmation.
Install only if you want repo-local ClawHub and Convex maintainer workflows. Review commands before running moderation, publishing, deployment, or migration steps, and consider using the autoreview helper's no-yolo mode if you do not want nested Codex review to run with full filesystem and sandbox bypass privileges.
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.
Static analysis
No suspicious patterns detected.