ClawHub
Back to skill

Security audit

memory-palace-architect

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only memory palace design guide with no hidden execution, credential access, or external data handling.

Before installing, expect this skill to help structure mnemonic memory-palace designs. Its broad triggers may activate it for generic memory or organization requests, and its example commands refer to plugin scripts that are not included in this submitted artifact, so run only commands you can verify in your installed plugin environment.

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
98% confidence
Finding
The trigger list includes generic words like "memory," "organization," "spatial," "knowledge," and "architecture," which are common in everyday requests and not narrowly scoped to this skill. Although the markdown later explains when to use the skill, the manifest does not provide tighter trigger constraints or exclusion examples, increasing the risk of unintended invocation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.