Security audit
Mixpanel
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is coherent and disclosed, but it includes powerful repo-maintainer and moderation workflows that users should run deliberately.
Use this only for the intended ClawHub/Convex maintainer workflows. Before running moderation, PR publishing, deployment, or auth setup commands, confirm the target account/repo/environment and understand that existing local credentials may be used. For autoreview on sensitive repos, consider `--no-yolo` or `AUTOREVIEW_YOLO=0` to avoid nested full-access review.
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.