ClawHub
Back to skill

Security audit

DoctorClaw Meeting Prep

Security checks for vulnerabilities and agentic risk

Overview

This meeting-prep skill is transparent about using calendar, email, CRM, task, and notes context, but users should configure those sensitive sources carefully.

Install only if you are comfortable granting meeting-prep access to the configured calendars and optional email, CRM, task, and notes sources. Prefer on-demand mode first, limit email lookback, avoid sending sensitive briefs to shared Telegram or Discord channels, and confirm where saved meeting notes and created tasks will live.

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
  • 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
95% confidence
Finding

The skill advertises automatic meeting preparation by scanning calendar events and then pulling email, CRM/contact notes, tasks, and prior meeting notes, but it does not clearly warn users that this involves broad access to sensitive personal and business data. Because the feature is designed to run automatically before meetings, users may not realize the scope of collection and correlation across multiple private sources, increasing the risk of overexposure or unintended data handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill states that after meetings it may prompt for notes, save those notes to memory, and create follow-up tasks, but it does not warn users that sensitive meeting outcomes may be persistently stored or transformed into automated actions. This can expose confidential discussion details, create inaccurate records, or trigger unwanted task creation without users fully understanding the persistence and downstream effects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.