ClawHub
Back to skill

Security audit

Mem0 Memory Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent memory-management helper, but users should understand it stores personal work context persistently in Mem0.

Install this only if you want Mem0 to retain reusable profile context across sessions and agents. Review stored memories periodically, delete stale or sensitive entries, and do not provide credentials, secrets, confidential business data, or information you would not want reused later.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises persistent cross-session storage of identity, preferences, rules, tech stack, projects, and relationships, but it does not provide a clear upfront disclosure about retention, scope, or privacy implications before collection begins. This is dangerous because users may share sensitive personal or organizational context without informed consent, increasing the risk of oversharing, unintended persistence, and downstream exposure through export or handoff features.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The onboarding flow instructs the agent to store each answer immediately after the user responds, yet it does not require an upfront warning or explicit consent for persistent retention. This is risky because users may answer conversationally without realizing each response is being durably recorded, including potentially sensitive employment, project, or preference data that could later be surfaced in reviews, exports, or agent handoffs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.