Security audit

Skill Finder CN Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ClawHub skill search helper that discloses its use of the ClawHub CLI and does not show hidden, persistent, or destructive behavior.

Before installing skills found through this helper, inspect the recommended skill and approve any install step deliberately. Users who prefer English-only output may find the bundled search script's Chinese messages inconvenient.

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 (4)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are broad enough to match ordinary requests about finding tools or getting help, which can cause the skill to activate outside its intended scope. Because this skill recommends and installs third-party skills, overly broad activation increases the chance of unsolicited repository lookups or steering users toward package installation when they did not explicitly ask for ClawHub skills.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The invocation guidance uses ambiguous phrases such as '有没有 skill 可以...' and '我需要一个能...的 skill' without defining boundaries, making accidental activation likely during normal conversation. In the context of a skill whose workflow includes search, inspection, and installation suggestions, this ambiguity can funnel users toward discovering or installing unvetted third-party capabilities they did not intentionally request.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The script includes user-facing text only in Chinese in the comment/description and runtime messages (`搜索脚本`, `用法`, `搜索`). This imposes a specific language on all users without offering a language choice or documenting that the skill is intended only for a Chinese-speaking or region-specific context.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The package name and bilingual description explicitly label the skill as "CN," indicating a China-specific language or locale targeting, but the file provides no user choice or documented justification for this locale constraint. Under the policy, forcing a specific language or locale without opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.