Build Managed It Services Provider Service Comparison Landing Page
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent maintainer and Convex-development workflows with no evidence of hidden exfiltration or destructive behavior, though some commands are powerful and should be used deliberately.
Install only if you want an agent to follow ClawHub maintainer and Convex project workflows. Pay special attention to the moderation skill, which can affect user accounts and public skill visibility, and the autoreview helper, which defaults to running nested Codex review with full filesystem/sandbox-bypass privileges unless invoked with --no-yolo or AUTOREVIEW_YOLO=0.
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.