ClawHub

Knowledge Graph - Kg Schema From Text

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent knowledge-graph schema helper with no evidence of hidden data transfer or unsafe behavior.

Reasonable to install if you want local help designing knowledge-graph schemas from text. Review any domain text you provide because the script may echo or transform it in output, but the skill does not show network transmission or hidden persistence.

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
Findings (1)

Exfiltration Commands

High
Category
Prompt Injection
Content
Posts can be shared by users and tagged with hashtags.
Users can form groups and invite other users.
Each user has a profile with personal information.
Users can send messages to each other.
```

### Generated Schema
Confidence
90% confidence
Finding
send messages to

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal