Security audit

chinese-sentence-correction

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow Chinese sentence-correction skill with no code, tools, persistence, or data access beyond the text the user provides.

Install this only if you want a specialized Chinese 病句 correction behavior. It is intentionally terse and returns corrected text without explanation, so users who want teaching notes or multilingual correction may prefer a broader writing skill.

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

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 (2)

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The instruction "用于中文病句修改" establishes a Chinese-only operating mode, and the file does not provide any user opt-in or language-selection mechanism. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is explicitly justified.

Natural-Language Policy Violations

Medium

Confidence: 80% confidence
Finding: The output requirements constrain the skill to return only the corrected sentence, and throughout the document that sentence is implicitly Chinese. Because no alternative language handling or user choice is offered, the skill enforces a locale-specific interaction pattern without opt-in.

Static analysis

No suspicious patterns detected.