Security audit
Script Coverage Reader
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent workflow helpers, but one review helper defaults to launching a nested Codex process with approvals and sandboxing disabled.
Install this only in a trusted ClawHub maintainer environment. Before using autoreview, prefer `--no-yolo` or `AUTOREVIEW_YOLO=0` unless you intentionally want a nested reviewer with full local authority. Keep GitHub, ClawHub, and Convex credentials least-privileged, and manually confirm moderation or publishing actions before they run.
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
51/51 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.