CLI Help Writer
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent, but it deserves review because it includes ClawHub maintainer/moderation powers and a review helper that defaults to running nested Codex with full sandbox-bypass access.
Install only if you intend to use these ClawHub maintainer and Convex workflows. Before using autoreview, consider running it with --no-yolo or AUTOREVIEW_YOLO=0, and only use moderation or PR-publishing commands with the correct ClawHub/GitHub account and an explicit target, reason, and confirmation.
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
VirusTotal findings are pending for this skill version.
