ai-meeting-notes

• Outcome: Review
• Latest audit: May 29, 2026 at 9:34 PM UTC
• Version:
  1.0.0

Overview

This meeting-notes skill appears to grant and promote broader third-party API access than its narrow purpose requires, while under-disclosing handling of sensitive meeting content.

Review this skill carefully before installing. Use it only if you are comfortable sending meeting audio, transcripts, and notes to SkillBoss, and avoid confidential, regulated, or personal meetings unless the publisher provides clear data-handling terms and narrowly scoped API access.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 97% confidence
• Finding: The skill is marketed narrowly for meeting notes, but its setup instruction auto-configures access to hundreds of APIs spanning unrelated domains. That violates least privilege and creates a capability mismatch where invoking a benign-seeming skill may silently grant much broader external access than the user would reasonably expect.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: Advertising scraping, social data, email, image, video, and other unrelated capabilities under a meeting-notes skill expands the attack surface without a justified business need. If an agent installs this skill expecting only note-taking, the broader capability set could be abused for unrelated data exfiltration or external actions.

Context-Inappropriate Capability

Low

• Confidence: 90% confidence
• Finding: The promotional section reinforces that the backing service includes scraping, social data, and other non-meeting APIs, which is inappropriate for the declared purpose of the skill. Even if framed as marketing, this normalizes excess privilege and may lead agents or users to trust a narrowly labeled skill with broad backend powers.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: The trigger language 'USE THIS when the user needs ai meeting notes' is broad and imperative, increasing the chance of automatic invocation in contexts where the user did not explicitly consent to third-party processing. For meeting content, accidental activation is more dangerous because transcripts and summaries often contain sensitive business or personal information.

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The skill does not warn users that meeting transcripts, recordings, or notes may be sent to a third-party API. Because meetings frequently contain confidential, regulated, or personal information, omission of this disclosure creates a significant privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.