ClawHub
Back to skill

Security audit

MeetingPrep Auto-Generate Meeting Briefs

Security checks for vulnerabilities and agentic risk

Overview

This meeting-brief skill is purpose-aligned and does not show hidden execution or exfiltration, but users should be deliberate about what calendar, email, note, and document access they allow.

Install only if you are comfortable with your agent using existing calendar and file-access tools for meeting preparation. When invoking it, specify the exact meeting and sources to use, and avoid broad requests that could pull unrelated emails, notes, or documents.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding
The skill promises automatic calendar access, context retrieval, and briefing generation from integrated sources, but the described behavior appears to be largely template-based and dependent on user-provided input. This mismatch is dangerous because users may grant trust and sensitive access under the assumption that the skill performs bounded, well-understood actions, when in reality its capabilities and data handling are unclear and potentially misleading.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The README says the skill surfaces context from calendar data, notes, emails, and documents, but it does not clearly warn users what sensitive data may be accessed, correlated, or included in generated meeting briefs. In a meeting-prep skill, this can expose private content about attendees or unrelated documents through over-collection or unexpected summarization, especially because the product is explicitly designed to use broad existing platform access.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The invocation text is broad and underspecified for a skill that may access calendars, files, notes, emails, and attendee-related context. Vague triggering instructions can cause overbroad data access, unintended collection of sensitive meeting information, or user confusion about what the agent will search and summarize.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises use of built-in calendar and file access plus surfacing of related context, but it does not clearly warn that sensitive personal or corporate data may be accessed, processed, and summarized. In a meeting-prep context, this is especially risky because calendars, attendee lists, notes, and linked documents often contain confidential business information and personal data.

Scope Creep

Low
Category
Excessive Agency
Content
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Scope Creep

Low
Category
Excessive Agency
Content
**USE AT YOUR OWN RISK.**

- The author(s) are NOT liable for any damages, losses, or consequences arising from 
  the use or misuse of this software — including but not limited to financial loss, 
  data loss, security breaches, business interruption, or any indirect/consequential damages.
- This software does NOT constitute financial, legal, trading, or professional advice.
- Users are solely responsible for evaluating whether this software is suitable for
Confidence
70% confidence
Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Static analysis

No suspicious patterns detected.