ClawHub
Back to skill

Security audit

risk-classification

Security checks across malware telemetry and agentic risk

Overview

This documentation-only skill helps label task risk and does not install code, access secrets, or perform actions by itself.

Before installing, be aware that generic triggers like risk, safety, and verification may make the skill appear during unrelated work. Review its risk labels rather than treating the GREEN default as a substitute for judgment on security, data, or production changes.

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
92% confidence
Finding
The trigger list includes broad, everyday terms such as "risk," "classification," and "safety," which are likely to match many unrelated user requests and cause unintended skill activation. In this context, accidental invocation is meaningful because the skill can influence task routing and default decisions, including implicitly treating tasks without metadata as GREEN, which could bias downstream safety handling.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.