Security audit
SKU Rationalization
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent repo-maintenance and Convex-development helpers, but one bundled review helper defaults to running a nested Codex review with full sandbox bypass authority.
Review before installing if you do not want a skill that can guide staff moderation, production deployment/auth work, and PR publishing. For autoreview, prefer running the helper with `--no-yolo` or setting `AUTOREVIEW_YOLO=0`, and only use moderation/deploy/migration commands after confirming the exact target, reason, environment, and rollback path.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.