ClawHub
Back to skill

Security audit

memclaw-maintance

Security checks for vulnerabilities and agentic risk

Overview

This memory-maintenance skill is not clearly malicious, but it asks for broad persistent control over future memory behavior and uses an unpinned plugin install path.

Review this carefully before installing. Only use it if you are comfortable making MemClaw the default memory system, storing and indexing user profile/session data persistently, and sending relevant memory content to your configured LLM and embedding providers. Pin or verify the plugin package where possible, back up existing memory and AGENTS.md files, and run maintenance in dry-run mode before allowing changes.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:100
Finding

Persistent Agent Instruction and Memory Workflow Hijacking

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:39
Finding

Unpinned Third-Party Plugin Installation

Content
View full analysis
Remediation
View remediation

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 (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 86)May include surrounding context.

md
"enabled": true,
        "config": {
          "llmApiKey": "your-llm-api-key",
          "llmApiBaseUrl": "https://api.openai.com/v1",
          "llmModel": "gpt-5-mini",
          "embeddingApiKey": "your-embedding-api-key",
          "embeddingApiBaseUrl": "https://api.openai.com/v1",

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md
"enabled": true,
        "config": {
          "llmApiKey": "your-llm-api-key",
          "llmApiBaseUrl": "https://api.openai.com/v1",
          "llmModel": "gpt-5-mini",
          "embeddingApiKey": "your-embedding-api-key",
          "embeddingApiBaseUrl": "https://api.openai.com/v1",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The maintenance example explicitly sets dryRun: false while invoking destructive or modifying operations like prune, reindex, and ensure-all, but it does not clearly warn that these actions can alter or delete local memory index/state. In a maintenance skill, users may copy-paste the example directly, causing unintended modification of persistent memory data or loss of recoverability if they expected a safe preview.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.