Back to skill

Security audit

Auto Meeting Minutes

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only meeting-minutes skill that formats user-provided transcripts and does not request code execution, credentials, persistence, or external access.

Before using this skill, avoid pasting unnecessary confidential, regulated, or personal details into meeting transcripts. Review the generated minutes before sharing because the skill intentionally produces concise minutes without extra disclaimers.

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
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description, headings, trigger phrases, output schema, and interaction rules are all specified in Chinese, and the instructions require a fixed output format in Chinese. There is no indication that users may choose another language or that the Chinese-only constraint is intentionally limited to a justified regional use case.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill is explicitly designed to process meeting transcripts, which commonly contain sensitive business information, employee names, decisions, and action items, yet it provides no privacy warning, minimization guidance, or handling constraints. In this context, users may paste confidential or personal data into the system without understanding the exposure risk, increasing the chance of unintended disclosure or over-sharing.

Content

No source excerpt is available for this finding.