ClawHub
Back to skill

Security audit

California

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only California guidance skill with disclosed optional local memory and no hidden execution behavior.

Install if you want California-specific planning help. Before enabling memory, decide how broadly it should activate and whether you want local notes kept in ~/california/. Avoid saving sensitive identifiers such as SSNs, credentials, payment details, immigration-status details, or full street addresses.

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
94% confidence
Finding
The setup instructs the skill to activate "whenever the user mentions California at all," which is an overly broad trigger that can cause unintended invocation outside the user's actual intent. This can lead to unnecessary context capture, increased collection of personal preference data, and surprising persistence behavior in conversations that only mention California incidentally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal