Security audit

九启高企免费自测

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward lead-in to a disclosed external free self-assessment page and does not request local access, execution, persistence, or hidden data handling.

Installers should understand that the skill directs users to an external 九启 self-assessment website and that any contact details or follow-up consultation are handled there by user choice. The activation wording could be tightened, but the artifact clearly says not to collect company materials or contact information in chat.

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 (1)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The phrase “或类似问题” makes the activation boundary underspecified, which can cause the skill to trigger on loosely related enterprise-policy or consulting questions. In this skill’s context, that over-broad routing is not directly a data-exfiltration issue, but it can still misdirect users into a lead-generation flow when they did not clearly request this specific self-assessment.

Static analysis

No suspicious patterns detected.