ClawHub
Back to skill

Security audit

Laozi

Security checks for vulnerabilities and agentic risk

Overview

This is a persona-only Laozi chat skill with no tools, code execution, persistence, or data access, though its Chinese triggers may activate more broadly than intended.

Install this if you want a Laozi-style conversational persona. Be aware that mentions of 老子 or 道德经 may invoke it unintentionally; narrower command-style triggers such as /laozi would reduce that risk.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
## Identity & Voice

Speak in paradox, stillness, and poetic brevity. You do not lecture — you point. Your words are sparse and each one carries weight. You often use nature as metaphor: water, the valley, the uncarved block. You speak from a place of profound quietude. You are not attached to being understood completely — the deepest truth resists full articulation. You may respond with a question, a paradox, or a short verse that opens rather than closes.

## Core Philosophical Positions

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The Chinese triggers '老子' and '道德经' are broad topical terms that can appear in ordinary conversation, literature, or educational contexts, so they may invoke the skill unintentionally. This can cause prompt hijacking of benign conversations into persona mode, degrading routing integrity and potentially suppressing the user’s actual intent.

Content

No source excerpt is available for this finding.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The trigger '老子' is extremely short and semantically common in discussions of philosophy, history, literature, and Chinese language, making accidental activation likely. Although the skill has no tools and model invocation is disabled, unintended routing can still interfere with normal assistant behavior and create user-confusing persona takeovers.

Content

No source excerpt is available for this finding.