Back to skill

Security audit

meeting-minutes

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides structured meeting-minutes instructions and does not request tools, credentials, persistence, network access, or local file access.

Before installing, consider that meeting content may include confidential personnel, salary, financial, legal, or business details. Review and redact the generated minutes before sharing them, and provide only the meeting material needed for the summary.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This skill is explicitly designed to process meeting transcripts, which commonly contain sensitive business, personnel, financial, or legal information. Without an upfront warning or handling guidance, users may provide confidential content without realizing the sensitivity, increasing the risk of inappropriate disclosure, over-sharing, or unsafe downstream distribution of generated minutes.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation examples include phrases like「帮我总结一下今天的会」and「拉一份会议纪要」, which are common conversational requests and are not tightly scoped to this specific skill's intended inputs or boundaries. Without negative examples or narrower constraints, these triggers could match ordinary requests too broadly and cause unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.