Back to skill

Security audit

AI会议纪要生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple meeting-minutes skill whose sensitive data handling is mostly expected for its purpose, but users should understand meeting content may be processed by AI APIs and saved to files.

Before using this skill, treat meeting audio and transcripts as sensitive: confirm participant consent, avoid highly confidential content unless your organization permits API-based processing, and review or delete generated minutes files as needed. Also note that this artifact does not include the referenced scripts/minutes.mjs implementation, so functionality may be incomplete unless supplied elsewhere.

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
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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README states the skill uses Whisper API and GPT API, but it does not warn users that meeting audio or transcripts may be transmitted to third-party services for processing. Because meeting data often contains sensitive business or personal information, this omission can lead to uninformed disclosure and privacy/compliance risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language instructions and description are presented exclusively in Chinese, which can amount to a language-policy issue when no user choice or opt-in is provided. The file does not indicate that the skill is intentionally region-specific or that alternative language support is available.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly processes meeting recordings and transcripts and writes generated minutes to output files, but the user-facing description and usage guidance do not warn about privacy, confidentiality, or local file output. This can lead users to submit sensitive meeting content without understanding that confidential information may be transcribed, summarized, and persisted to disk.

Content

No source excerpt is available for this finding.