Security audit

life-restart-pro

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only entertainment skill for generating fictional life-simulation stories, with no hidden code or high-impact permissions.

Before installing, be aware that ordinary phrases about restarting or alternate lives may trigger the simulator. It does not need external tools; only allow file access if you actually want it to save a simulation record.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Tp2

High

Category: MCP Tool Poisoning
Confidence: 85% confidence
Finding: Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The activation phrases are broad enough to match ordinary conversation about life choices or hypothetical scenarios, which can cause the skill to trigger when the user did not explicitly request it. In an agent environment, overbroad invocation can hijack intent routing, override more appropriate skills, and produce unexpected content without clear consent.

Vague Triggers

Low

Confidence: 89% confidence
Finding: The restart condition allows very generic phrases like '再来一次' or 'restart' to re-enter the skill without confirming that the user is still interacting with this specific simulation. This can create accidental re-triggering during unrelated dialogue, causing context confusion and unintended skill persistence.

Static analysis

No suspicious patterns detected.