Back to skill

Security audit

Heleni Meetings

Security checks for vulnerabilities and agentic risk

Overview

This meetings skill is useful and not malicious, but it can save sensitive meeting transcripts and modify calendar or task files without strong upfront consent or retention controls.

Review this skill before installing if your meetings may include confidential, legal, HR, financial, or personal information. Consider editing it to ask before saving notes, omit raw transcripts by default, preview calendar and todo.md changes before applying them, and limit previous-meeting searches to the meeting-notes folder unless you explicitly choose a broader search.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrase "take notes" is overly generic and can match common conversational requests unrelated to this skill, increasing the chance of accidental activation. In this skill, unintended activation is more concerning because it can lead to note storage, transcript handling, and downstream file modifications without the user explicitly intending to invoke the meetings workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill directs saving meeting notes and raw source material to workspace files without first warning the user that potentially sensitive meeting content will be retained on disk. Because meeting notes and transcripts often contain confidential business information, this creates a real privacy and data-retention risk if the user did not explicitly consent to storage.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Preserving the original meeting notes or transcript verbatim in saved files can retain secrets, personal data, legal discussions, or other sensitive content in plain text. This is especially risky in a meetings skill because users may paste highly confidential raw notes, and the saved <details> section creates a durable copy beyond the immediate interaction.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs adding selected action items to todo.md, which modifies a workspace file, but does not clearly warn the user up front that a file write will occur. Although the prompt asks which items to add, the lack of explicit modification notice can still surprise users and cause unintended persistence of potentially sensitive tasks.

Content

No source excerpt is available for this finding.