Security audit

Business Ideas

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent business-idea assistant that uses a small local folder to remember generated ideas and preferences.

Before installing, be comfortable with the skill keeping generated business ideas, favorites, rejection notes, and preferences in ~/business-ideas/. Avoid storing confidential plans there unless you are willing for your local agent sessions to reuse them, and ask the agent before saving if you want tighter control.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Missing User Warnings

Low

Confidence: 90% confidence
Finding: The skill explicitly establishes a persistent memory directory under the user's home folder, but it does not clearly warn the user that invoking the skill may create and modify local files. This is a real safety issue because silent persistence can surprise users, leak sensitive preferences or idea history into disk storage, and normalize file modifications without informed consent.

Missing User Warnings

Low

Confidence: 95% confidence
Finding: The 'Update Memory Proactively' section instructs the agent to append, move, and update user files automatically based on conversation events, without a clear opt-in boundary. Even in a benign productivity skill, autonomous writes to local storage can cause unintended data retention, overwrite expectations, and privacy issues if sensitive business ideas or preferences are persisted without explicit approval.

Missing User Warnings

Low

Confidence: 87% confidence
Finding: This markdown file directs the skill to create a directory and multiple files under the user's home directory, which affects user data and the local filesystem. The instructions do not include any warning or disclosure that setup will write to disk or modify files.

Static analysis

No suspicious patterns detected.