Back to skill

Security audit

Data Privacy Agreement

Security checks across malware telemetry and agentic risk

Overview

The reviewed artifacts are coherent maintainer and Convex workflow skills with sensitive actions disclosed and gated by user direction or existing auth.

Install only if you are comfortable with maintainer/developer workflows that can modify project files, run package and Convex commands, and perform authenticated ClawHub admin actions. Read commands before approving them, especially moderation, email, migration, deploy, and full-access review-helper runs.

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

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.