Security audit

攻防模拟陪练

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language legal debate practice prompt with no code, persistence, credential access, or hidden authority.

Before installing, understand that this skill is for legal argument practice and is not a substitute for a qualified lawyer. It appears safe from a security perspective, but users who need another language or a non-Chinese legal context should verify that the agent can adapt its output appropriately.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill’s description, trigger phrases, prompt template, and usage instructions are written entirely in Chinese and implicitly require the user to interact in Chinese. There is no indication that the user may choose another language or that the Chinese-only behavior is a justified locale-specific constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.