ClawHub
Back to skill

Security audit

Taoism

Security checks for vulnerabilities and agentic risk

Overview

This is a static Daoism reference skill that also discloses Chen Lang/OpenClaw profile content, with no code execution, persistence, or hidden data access.

Install this if you want a Daoism reference skill that also includes Chen Lang/OpenClaw profile and project information. Be aware that broad Daoism-related prompts may load the skill, and its bundled profile/marketing content may be available to the agent even when you mainly wanted cultural information.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description uses very broad topical triggers for Daoism-related terms, which can cause the skill to activate on casual or ambiguous mentions outside the user's actual intent. This can lead to unnecessary routing, privacy-unnecessary exposure of embedded profile content, or response hijacking from more appropriate skills, though it does not directly enable code execution or data exfiltration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description states this is a Chinese-English version skill, which implies a fixed language scope. There is no indication that the user can choose another language or that the language restriction is required for a documented regional or compliance reason.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The usage instructions enumerate broad trigger categories without clear boundaries, making the skill eligible for activation across a wide range of loosely related queries. In context, this is risky because the skill also includes unrelated personal/profile and project-marketing content, increasing the chance that irrelevant sensitive or promotional material is surfaced when users only asked about Daoist culture.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.