ClawHub
Back to skill

Security audit

Meeting Prep

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward meeting-prep assistant, but users should know it may research people online and use prior notes or CRM data if available.

Install this if you want automated meeting briefs. Before using it with real contacts, decide whether the agent may search public profiles and access internal notes or CRM records, and ask it to limit briefs to meeting-relevant facts.

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)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger examples are broad enough that the skill may activate on loosely related requests about people or companies, causing the agent to begin external research and compile briefing material without sufficiently clear user intent. In this skill, that increases the chance of unnecessary collection or use of personal, web-sourced, prior-note, or CRM-derived information in contexts where the user may not have explicitly asked for that level of profiling.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to research attendees, pull prior notes, and use CRM data, but it does not warn users that personal information and internal relationship history may be gathered and surfaced. That omission creates a privacy and data-governance risk because sensitive internal or personal data could be processed or revealed without informed user awareness or explicit confirmation.

Static analysis

No suspicious patterns detected.