ClawHub
Back to skill

Security audit

Atomic Memory Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward memory helper that reads and writes OpenClaw workspace memory, with no hidden code or installation behavior found.

Install this if you want agents to use OpenClaw workspace memory for prior decisions, preferences, todos, and durable notes. Be cautious about asking it to store secrets, because persistent memory can affect later sessions.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description has broad activation triggers such as prior work, decisions, dates, people, preferences, todos, and storing durable notes, which can match many ordinary user requests across unrelated tasks. In an agentic system, this overbroad routing can cause the memory skill to activate unnecessarily, increasing the chance of inappropriate memory reads or writes and expanding exposure of stored contextual data beyond least-privilege use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.