Security audit

她这话什么意思 · 直男聊天急救手册

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese relationship-chat coaching skill that stays within user-provided conversation advice and does not request device, account, or messaging authority.

Install this only if you want a Chinese-language assistant for relationship message interpretation. Avoid pasting unnecessary personal details, and remember it provides suggested wording only; you remain responsible for whether and how to send any message.

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 (2)

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger list contains very broad, conversational phrases such as "她是不是喜欢我" and "怎么约她出来," which are common in ordinary chats and can cause the skill to activate when the user did not intend to invoke this specialized behavior. Unintended invocation can lead to privacy issues if personal relationship content is processed unexpectedly, and it can override a more appropriate general-purpose assistant response.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill is authored entirely in Chinese and presents a fixed Chinese-language interaction model without offering a language choice or fallback. This can cause unintended behavior for users in other locales, including misunderstanding of safety guidance or incorrect execution of the skill’s required structured workflow.

Static analysis

No suspicious patterns detected.