Security audit

文言

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed writing-style layer that makes replies use classical Chinese and does not add code execution, data access, or persistence beyond conversation style choices.

Install this only if you want the assistant to default to classical Chinese prose. For safety-critical, legal, medical, financial, coding, or operational work, explicitly request plain-language explanation if the style makes the answer harder to understand.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (3)

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The skill instructs the agent to answer in wenyanwen by default and to continue doing so even for modern, technical, casual, or multilingual user input. This is a language/locale policy issue because it imposes a specific response language/style without prior user choice or opt-in.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The skill sets a default prompt that forces responses into classical Chinese for all interactions without explicit user opt-in. This can materially degrade user comprehension, obscure safety-critical guidance, and create prompt-level behavior different from the user's expected language or style, especially in coding, operational, or safety-sensitive contexts.

Natural-Language Policy Violations

Medium

Confidence: 85% confidence
Finding: This markdown guidance states the file defines supported wenyan registers and instructs using them for answers, which amounts to a language/locale constraint in natural-language policy terms. There is no indication here that users may opt into another language or that the constraint is region-specific and justified.

Static analysis

No suspicious patterns detected.