ClawHub
Back to skill

Security audit

Huo15 Openclaw Memory Curator

Security checks for vulnerabilities and agentic risk

Overview

This memory-maintenance skill is transparent about its purpose, but it can delete saved memories and update MEMORY.md without requiring explicit user confirmation first.

Review this skill before installing if you rely on saved memories. Use it only when you intend memory maintenance, and ask the agent for a preview of proposed deletions and MEMORY.md changes before allowing updates.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are broad enough to match ordinary requests about 'organizing memory' or 'cleaning expired memory', which can cause the skill to activate in situations where the user did not clearly intend destructive maintenance actions. In this skill, accidental activation is more dangerous because the documented workflow includes reviewing, deleting entries, and updating MEMORY.md, so an ambiguous match can lead to unintended data modification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs deletion of memory entries and synchronization into MEMORY.md, but it does not require a clear user warning, preview, or confirmation before modifying stored data. This is dangerous because users may invoke a maintenance-looking action without realizing it can permanently delete records or overwrite curated summaries, causing loss of important context and integrity issues in the memory system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language instructions and examples are entirely in Chinese, which can function as an implicit language constraint for use of the skill. The file does not offer users a choice of language or explain that the skill is intentionally limited to Chinese-speaking contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.