ClawHub
Back to skill

Security audit

OpenClaw Memory Format

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only memory-format guide; it discloses persistent memory files, but does not include hidden code, network behavior, or unsafe install actions.

Before installing, understand that this guide describes memory that can persist in workspace files and be searched later. Avoid putting secrets, credentials, personal data, or confidential prompts into memory, and periodically review or delete memory files you no longer want retained.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documents an automatic memory flush that appends conversation-derived content to disk, but it does not include safeguards, consent requirements, or warnings about persisting potentially sensitive user data. In an agent setting, this can lead to unintended retention of secrets, personal data, or confidential prompts in workspace files that may later be searched, reused, or exposed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.