ClawHub
Back to skill

Security audit

methodology-curator

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable methodology reference skill; its only notable issue is broad trigger wording that may activate it more often than intended.

Before installing, be aware that this skill may appear in general design or evaluation conversations because of broad triggers. The skill itself is reference material and does not run commands or access private data; treat the external Claude Code plugin mentioned in the text as a separate install decision.

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 trigger list contains broad, commonly used terms such as "design," "evaluation," and especially the fragmented phrase components "hooks" and "or agents," which can cause the skill to activate in many unrelated conversations. Over-broad invocation increases the chance that this skill intercepts workflows unexpectedly, creating prompt-routing confusion and possible interference with more appropriate security-sensitive or task-specific skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.