ClawHub
Back to skill

Security audit

OpenClaw session maintain helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small session-maintenance helper with disclosed, purpose-aligned behavior, though users should be aware that reset actions can disrupt current context.

Install this only if you want an assistant to help manage OpenClaw session state. Before using /reset, confirm what context may be cleared, since the skill is less strict about reset confirmation than it is for /compact or /new.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes broad, natural-language phrases such as "fresh slate" and "session feels stale," which can cause the skill to activate when a user is speaking descriptively rather than explicitly requesting a session action. In this skill’s context, unintended activation is risky because the associated operations can disrupt or replace session state, potentially causing loss of context or workflow interruption.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill treats /reset as a disruptive session operation but only says confirmation is "recommended" rather than required, creating an inconsistent safeguard for a state-altering action. A mistaken or unintended reset could clear active session state and interrupt the user’s work, especially if triggered by ambiguous language or automation.

Content

No source excerpt is available for this finding.