Back to skill

Security audit

Ai Linguistics

Security checks across malware telemetry and agentic risk

Overview

The artifact is a coherent set of ClawHub maintenance and Convex workflow skills with sensitive operations clearly scoped and gated by user/admin confirmation.

Install only if you work on ClawHub or Convex workflows and understand that some skills can guide admin moderation, production migration, email, and external code-review actions. Keep normal CLI authentication controls in place and require the documented dry runs and confirmations before any write, email, or production operation.

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.

View on VirusTotal

Static analysis

No suspicious patterns detected.