ClawHub
Back to skill

Security audit

Weiliaozi Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, read-only structured analysis skill with no executable code, persistence, or hidden data movement found.

Installers should expect a read-only analysis helper that may use provided files or web lookup for context. For sensitive business, political, military, or competitive scenarios, treat its output as structured analysis rather than authoritative advice and verify important facts independently.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example explicitly documents a trigger-based mode switch for historical questions that opens with a fixed Chinese phrase ("臣缭以为") and maintains a prescribed structure, without indicating that this behavior requires explicit user opt-in. In an agent skill, hidden trigger guidance can override user language or style expectations and create prompt-routing behavior that is not transparent to the user, reducing controllability and potentially causing unintended instruction following.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and all recommended stylistic anchors are written as Chinese output requirements, and the file presents them as the default way the skill should respond. Because it does not offer user opt-in or explain a region-specific need, this creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The package description is written entirely in Chinese, which can impose a language-specific experience on users without indicating any option to choose another language. Although later keywords mention bilingual support, the primary user-facing description here does not offer a language choice or explain the locale expectation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.