ClawHub
Back to skill

Security audit

Model

Security checks across malware telemetry and agentic risk

Overview

This is a plain guidance-only skill about AI models and prompting, with no code, credentials, install hooks, or privileged behavior.

This appears safe to install as general AI-model and prompting guidance. Treat its model comparisons, pricing, and capability claims as advice that may become outdated, and verify current facts before making important technical or financial decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description is extremely broad and can match a wide range of ordinary AI-related queries such as choosing models, prompting, evaluation, and workflows. In systems that auto-activate skills from natural-language descriptions, this increases the chance the skill is invoked in unintended contexts, creating overreach, routing ambiguity, and possible interference with more specialized skills or policies.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.