Security audit

ai-conversation-optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language prompt-improvement guide with broad but disclosed routing language and no code, persistence, credential use, or system access.

Install this if you want a Chinese-language assistant for improving prompts. Be aware it may activate for fairly general requests about improving AI questions, and it does not provide multilingual guidance unless the agent adapts it separately.

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill metadata and content prescribe Chinese-language behavior without any indication that the user's language preference should be respected. This can degrade usability, cause unintended language switching, and in multilingual environments may leak or mishandle content by transforming user input into an unexpected language context.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are very broad and match common help-seeking requests such as improving a question or getting better AI answers. In a skill-routing system, this can cause the skill to activate unexpectedly and steer ordinary conversations into a rigid prompt-optimization workflow, potentially overriding user intent or interfering with other more appropriate skills.

Natural-Language Policy Violations

Low

Confidence: 85% confidence
Finding: This markdown file contains user-facing guidance only in Chinese and does not indicate that the language requirement is optional or limited to a specific regional audience. Under the policy rule for language or locale constraints, forcing a single language without opt-in can be a natural-language policy concern.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: This markdown file presents all instructions and examples exclusively in Chinese, which can amount to forcing a specific language without user opt-in. The policy allows locale constraints when explicitly justified or optional, but no such choice or justification appears in the file.

Static analysis

No suspicious patterns detected.