ClawHub
Back to skill

Security audit

rules-eval

Security checks across malware telemetry and agentic risk

Overview

This skill is a rule-auditing guide with no executable code, persistence, credential access, or hidden data handling, though its trigger terms are broader than ideal.

Before installing, be aware that this skill may activate for broad words like rules or validation. Its contents are otherwise limited to guidance for auditing Claude Code rule files, so review activation behavior if you use many similarly named skills.

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
85% confidence
Finding
The trigger list contains generic terms like "evaluation," "rules," and "validation," which are broad enough to match many unrelated user requests. This can cause the skill to activate outside its intended scope, increasing the chance that its instructions influence conversations unexpectedly or override more appropriate tooling.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.