ClawHub
Back to skill

Security audit

OpenClaw Partner Guide

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed assistant-behavior guide with small local summary-printing helpers and no hidden network, credential, destructive, or persistence code.

Install this if you want a general partner-style operating guide for an assistant. Review memory and scheduling permissions in your agent environment, because the guide encourages remembering durable context and creating scheduled continuations when useful.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description presents a comprehensive behavioral guide for how an OpenClaw assistant should operate in conversation and when taking actions. The supplied code does not implement those policies or controls. Instead, it is a simple renderer that accepts CLI inputs and prints a formatted 'Partner Handoff Summary.' While the output theme loosely relates to a partner-style workflow, the code’s primary purpose is materially different and much narrower than the declared assistant operating guide. There are no suspicious external accesses or hidden capabilities, but the description does not accurately represent the actual behavior of this code chunk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The phrases "Directly asked," "Mentioned explicitly," and especially "You add clear value" do not define a narrow invocation boundary and could cause the skill to speak in many ordinary chat situations. The file also lacks specific trigger examples or exclusion constraints beyond general silence guidance, making activation scope unclear.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.