Back to skill

Security audit

Skill Analyst Zh

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language assistant for comparing and reviewing OpenClaw skills before installation or publication.

Before installing, users should expect this skill to read local OpenClaw skill descriptions and run ClawHub lookup commands when asked to evaluate, compare, install, or publish a skill. Use explicit wording if you want to avoid accidental activation in casual discussion.

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
  • 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 advertises very broad trigger phrases such as “这个skill值得装吗”, “能发布吗”, and “skill对比”, which are common in normal conversation and not tightly scoped to an explicit invocation pattern. This can cause accidental activation, leading the agent to scan local skill directories or invoke external CLI tooling unexpectedly when the user did not intend to run this skill.

Content

No source excerpt is available for this finding.