Security audit

maozedong-founder-coach（毛泽东思想式创业教练）

Security checks for vulnerabilities and agentic risk

Overview

This is a visible Mao-themed business coaching skill, but it asks for broad file, shell, and web tool access that is not needed for its coaching purpose.

Review before installing. The coaching content is visible and mostly purpose-aligned, but install only if you are comfortable with this skill being allowed to read and modify files, run shell commands, and fetch web content when invoked; a safer version would remove those tools or require explicit confirmation before any file, shell, or web action.

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

High

Confidence: 94% confidence
Finding: The trigger phrases are very broad and overlap with ordinary entrepreneurship requests, which can cause the skill to activate in contexts where the user did not intend Mao-themed strategic framing. In an agent ecosystem, unintended activation can steer responses, distort user intent, and inject ideological or off-target guidance into normal business conversations.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger list includes broad, ordinary startup questions such as competition, user needs, and long-term strategy, which can cause the skill to activate when a user did not explicitly request Mao-themed guidance. That creates prompt-routing risk: users may receive ideologically framed or militarized advice unintentionally, and the broad matching may override more appropriate domain skills.

Static analysis

No suspicious patterns detected.