Security audit

Inspirations

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local idea-capture helper that saves structured notes in the workspace, with privacy considerations but no hidden execution or exfiltration behavior found.

Install this only if you want idea-like messages to be saved automatically as local Markdown notes. Do not use it for secrets, credentials, regulated personal data, or confidential plans unless you are comfortable with that text being retained in workspace/inspirations/ and the monthly index.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (3)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill is designed to automatically create files and append to a monthly index in the workspace without any explicit user-consent, notice, or data-handling warning. This can cause unintended persistence of user-provided content, including sensitive ideas or personal information, and the automatic append behavior broadens the retention surface.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The description and operational content are entirely specified in Chinese, including the required confirmation format and file content conventions, without indicating that users may choose another language or locale. This can violate a language/locale policy when the skill implicitly constrains interaction and generated content to a single language without opt-in.

Ssd 3

Medium

Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to store the user's raw input verbatim, which can capture secrets, personal data, confidential plans, or regulated information without filtering or minimization. In an idea-capture context, users are especially likely to share unstructured sensitive content, making persistent verbatim storage a meaningful privacy and data-retention risk.

Static analysis

No suspicious patterns detected.