Security audit

三万裁判

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language judging skill that only instructs the agent to return either “合格” or “不合格” based on an existing review result.

Install this only if you want a Chinese-language final judge that returns exactly 合格 or 不合格. It is very narrow and does not perform its own detailed review or provide explanations.

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

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The markdown explicitly requires output to be only the Chinese words “合格 / 不合格” and forbids any other text. This imposes a specific language choice without offering the user a language/locale option or documenting why a Chinese-only constraint is required.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.