ClawHub
Back to skill

Security audit

palace-diagram

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only diagram helper for memory-palace graphs, with no hidden execution or persistence found.

Before installing, confirm you want generic diagram or memory requests to potentially activate this skill. Use it only with palace data you intend to visualize, especially if rendering through Mermaid Chart MCP because the generated diagram may contain knowledge-graph details.

SkillSpector

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
95% confidence
Finding
The trigger list includes broad generic terms such as "memory," "diagram," "graph," and "visualization," which can cause the skill to activate in many unrelated contexts. Over-broad invocation increases the chance that the wrong skill handles user input, potentially exposing internal knowledge-graph content or causing unintended tool use in contexts where a palace diagram was not requested.

Static analysis

No suspicious patterns detected.