Security audit

Brainhole Factory

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only entertainment skill for generating fictional alternate-universe responses, with no code execution, persistence, or data access.

Install this if you want humorous fictional 'what if' content. Be aware it may trigger too easily on broad phrases like 'if' or 'what if', and its fake-news style sections should be treated as fiction rather than factual reporting.

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: 91% confidence
Finding: The description states the skill should activate whenever the user mentions broad keywords, without defining boundaries or intent checks. In practice, this ambiguous invocation model can make the agent spuriously enter a playful alternate-universe mode during serious, analytical, or safety-sensitive conversations.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger condition activates on very broad phrases like '假如', '如果', 'what if', '脑洞', and '平行宇宙', which are common in normal conversation and not narrowly scoped to this entertainment skill. This can cause unintended invocation, hijack unrelated user requests, and override the expected behavior of the host agent with irrelevant or misleading output.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: The instructions require “超详细英文 prompt”, which forces a specific language for part of the output. The file does not offer opt-in, fallback, or user choice for prompt language, so it creates a language-policy concern.

Static analysis

No suspicious patterns detected.