Back to skill

Security audit

memory-stack-gungun - AI 记忆栈

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language guide for building an AI memory architecture, with no executable code or hidden behavior found.

Before installing, understand that this is a Chinese-language memory architecture guide that discusses persistent memory files and knowledge indexing. Use it with explicit user control over what gets archived or promoted into long-term memory.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description and all user-facing instructional content are written almost entirely in Chinese, with no indication that users may choose another language or that the skill is intended only for a Chinese-speaking or region-specific audience. Under the policy, a language constraint should be optional or explicitly justified rather than implicitly imposed.

Content

No source excerpt is available for this finding.