Security audit

AI会议纪要生成器Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only meeting-minutes skill whose API-based handling of user-provided audio and transcripts is purpose-aligned, but users should treat meeting content as sensitive before sending it to external AI services.

Before installing, confirm you are comfortable sending meeting audio or transcripts to the AI providers named by the skill, and avoid using it for regulated or confidential meetings unless you have consent and an approved data-handling process. Also note that the submitted package references a Node script that is not included in the inspected artifact.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (4)

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The README states that meeting audio is processed by Whisper API and text is analyzed by GPT API, but it does not clearly disclose that potentially sensitive meeting content will be transmitted to third-party external services. For a meeting-minutes tool, this omission can mislead users into uploading confidential business, legal, HR, or personal discussions without informed consent, creating privacy, compliance, and data-handling risk.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly handles meeting recordings and transcripts, which commonly contain personal data, confidential business information, and sensitive discussions, yet the description provides no warning or handling guidance. This can lead users to process sensitive content without informed consent, retention controls, or redaction practices, increasing the risk of privacy or confidentiality exposure.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: SQP-3适用于所有文件类型。该技能说明全文均为中文，未提供多语言选项、用户选择机制，亦未说明该技能明确限定为中文场景，可能构成未经用户选择即强制特定语言的自然语言政策问题。

Natural-Language Policy Violations

Low

Confidence: 82% confidence
Finding: The natural-language description and usage guidance are presented exclusively in Chinese, which can impose a language constraint on users without any opt-in or justification. The file does not indicate that the skill is intended only for a Chinese-speaking or region-specific audience.

Static analysis

No suspicious patterns detected.