Back to skill

Security audit

audit-economic-responsibility

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language audit workflow template, not a package that hides execution, persistence, or data-exfiltration behavior.

Install only if you are comfortable using a Chinese-language audit workflow and have reviewed the external pipeline/scripts it depends on in your environment. Treat audit inputs and generated findings as sensitive, and have a qualified reviewer verify evidence, legal citations, and responsibility determinations before relying on outputs.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill's title, instructions, and example invocation are entirely in Chinese, including the user-facing phrase the user is told to say to OpenClaw. There is no indication that other languages are supported or that Chinese is a region-specific requirement, which creates a natural-language policy concern under the language/locale rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest content is entirely in Chinese, including the skill name, description, tags, category, and author-facing metadata, with no indication that users can choose another language or that the skill is intended only for a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without opt-in or documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.