Security audit
Gmail
Security checks across malware telemetry and agentic risk
Overview
The reviewed ClawHub helper skills disclose their maintenance and development workflows and do not show hidden harmful behavior.
Use these skills only in the intended ClawHub or Convex maintenance context. Before running moderation, migration, deploy, proof-publish, or autoreview commands, confirm the target, use dev/test environments when possible, keep credentials scoped, and use the autoreview no-yolo or fallback controls if you do not want broad local access or code diffs sent to external reviewer CLIs.
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.