Security audit

persona-simulator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language persona roleplay skill with no code, tool use, data access, persistence, or hidden install behavior.

Install this only if you want Chinese-language persona and roleplay responses. Be aware that common requests like asking for a style or roleplay may trigger it, and the default behavior is to keep speaking in a selected persona rather than explaining the rules.

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 (3)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill description includes broad, everyday trigger phrases such as '以XX风格回答', '模拟人格', and '角色扮演', which are common in normal conversation and can cause the skill to activate unintentionally. This can unexpectedly override the assistant’s normal behavior and response style, making routing less predictable and potentially interfering with other, more appropriate safety- or task-specific skills.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill content hardcodes Chinese-language behavior and interaction norms without offering language fallback or respecting the user’s current language. In multilingual environments, this can cause confusing or inaccessible behavior, and may unexpectedly change the assistant’s output language when the user did not request it, reducing usability and increasing the chance of miscommunication.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This markdown file defines persona instructions exclusively in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.