Back to skill

Security audit

OpenClaw: memory optimizer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent memory-configuration optimizer, but it tells agents to persistently change OpenClaw defaults and restart the gateway without enough user-control or rollback guidance.

Before installing, treat this as a Review item: only use it when you intentionally want persistent OpenClaw memory-search changes, back up ~/.openclaw/openclaw.json first, review any proposed config diff, and avoid gateway restart commands during active or shared sessions unless you have planned the interruption.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file’s operational description and user instructions are presented entirely in Chinese, with no indication of language choice or opt-in. Under the stated policy, forcing a specific language without offering alternatives is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to persistently modify OpenClaw configuration without warning that this changes user settings and may degrade recall, precision, or system behavior if misapplied. In agent environments, silent persistent configuration changes are dangerous because they can alter future behavior across sessions and are difficult to audit or roll back if no backup or review step is suggested.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The feature-flag examples restart the OpenClaw gateway without any warning about service interruption, transient unavailability, or impact on active sessions. This is dangerous in shared or production-like environments because a user following the instructions may unintentionally disrupt ongoing work or cause loss of in-flight state.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The manifest describes this skill as optimizing memory-search configuration parameters and periodically checking that configuration. However, the documented feature-flag workflow instructs users to restart the gateway process via openclaw gateway restart, which is a service-control capability rather than a direct memory parameter adjustment.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The markdown content is entirely written in Chinese and does not indicate that the skill or documentation is region-specific or that users may choose another language. Under the policy rule, forcing a specific language without opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.