ClawHub
Back to skill

Security audit

A-MEM Memory Organization

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently helps organize durable memory notes, with privacy caution because it can persist user or project context.

Install this only if you want the agent to maintain durable memory notes. Review what gets saved, avoid storing secrets or sensitive personal information, and prefer explicit prompts such as 'save this to memory' when you want persistence.

A.I.G

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

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s activation phrases are very broad (e.g. 'remember', 'keep context', 'organize knowledge') and overlap with ordinary conversation and routine assistant behavior. That can cause unintended invocation of long-term memory workflows, leading to over-collection, persistence of sensitive information, or memory-file modifications when the user did not clearly intend durable storage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.