Back to skill

Security audit

MemPalace记忆系统助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple memory-helper skill whose persistent storage and retrieval behavior matches its stated purpose, with privacy and accidental-trigger caveats users should understand.

Install only if you want a local persistent memory helper. Avoid storing secrets, credentials, or sensitive personal data unless you understand where mempalace stores its memory and who can later list or export it; use the explicit commands for add, search, list, and export deliberately.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation phrases include very broad natural-language terms such as “记住” and “搜索记忆”, which are likely to appear in ordinary conversation and can unintentionally trigger the skill. In a memory tool, accidental activation is more dangerous than usual because it can cause unintended storage, retrieval, or exposure of persistent user data across sessions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill exposes memory-writing and export capabilities but does not warn users that inputs may be persistently stored or later disclosed through listing/export. Because this skill is specifically designed for cross-session memory retention, omission of a privacy warning materially increases the risk of users entering sensitive data without informed consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.