ClawHub
Back to skill

Security audit

knowledge-locator

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for searching memory-palace knowledge, with broad triggers but no hidden execution, credential access, exfiltration, or destructive behavior found.

Install this if you use the related memory-palace workflow and want search/navigation guidance. Be aware that its generic triggers may activate during ordinary search or recall requests, so users may want narrower activation terms if they have many skills installed.

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 (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes generic terms like "retrieval," "search," "indexing," and "recall," plus a broad natural-language condition about "looking for previously stored information." These are common concepts in everyday assistance requests and the file does not provide constraints or negative examples to clarify when this skill should or should not activate.

Shadow Command Trigger

Medium
Category
Trigger Abuse
Confidence
70% confidence
Finding
Shadow Command Trigger: 'search' conflicts with built-in command 'search'

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.