Security audit

批判性思维·学会提问

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese-language critical-thinking guide with no executable code or privileged access.

Install this if you want Chinese-language help decomposing and evaluating arguments. If you prefer another language, explicitly ask the agent to answer in that language because the provided template is Chinese.

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown skill is written as an instruction/output template entirely in Chinese, and the example response format also requires Chinese section labels. Under the policy rule for language/locale, this constitutes a forced language choice unless the skill documents that it is intentionally region-specific or offers an opt-in/alternative language path.

Static analysis

No suspicious patterns detected.