Security audit

China Gaokao Public Data

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to gather official public Chinese university and major information, without requesting private data, code execution, persistence, or privileged access.

This skill appears safe to install for public Gaokao information lookup. Users should still remember that admissions rules change by year and province, and final decisions should be based on current official notices rather than the skill's summaries alone.

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 (1)

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The instruction states in Chinese that the agent is a public information assistant for Chinese Gaokao families, and the entire skill specification requires operation in Chinese without indicating that users may choose another language. The policy for this audit flags language or locale constraints when they are forced without user opt-in or a clearly documented justification.

Static analysis

No suspicious patterns detected.