ClawHub
Back to skill

Security audit

Meeting Debrief

Security checks for vulnerabilities and agentic risk

Overview

This skill is purpose-aligned for meeting debriefs, but users should be aware it saves a local diagram file and can optionally send meeting-derived details to a CRM.

Install only if you are comfortable letting the agent turn meeting transcripts into structured notes and a saved Excalidraw file. Before accepting any CRM offer, review what information will be sent, which CRM account will receive it, and whether contacts, notes, deals, or pipeline tags should be created or updated.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The CRM integration step encourages creating or updating contacts, logging notes, and creating deals based on meeting content, but does not require a privacy warning or explicit consent before transmitting transcript-derived data to external systems. Because meeting debriefs often contain sensitive personal, strategic, and commercial information, silent or lightly prompted export to HubSpot or Zoho could result in unauthorized disclosure to third parties.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to always generate and save an Excalidraw file in the current working directory without first obtaining explicit user consent or warning that disk writes will occur. This can cause unintended local file creation, overwrite conflicts, or persistence of potentially sensitive meeting content on disk, especially when transcripts contain confidential business information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.