ClawHub
Back to skill

Security audit

Meeting Prep Agent

Security checks for vulnerabilities and agentic risk

Overview

The skill matches meeting-prep work, but its proactive mode can automatically read sensitive calendar, CRM, notes, and financial files and persist briefs without clear user controls.

Install only if you are comfortable granting the agent access to sensitive meeting context. Keep proactive mode disabled unless you have scoped which calendars, CRM/notes, and financial files it may read, and review generated briefs before sharing them outside your workspace.

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
  • 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
Confidence
95% confidence
Finding
The skill enables proactive access to calendar, CRM/notes, financial records, and web research to generate meeting briefs without clearly requiring explicit user opt-in at the time of access. Because these sources can contain sensitive business and client data, automatic collection and synthesis increases the risk of overbroad data access, unexpected surveillance-like behavior, and accidental exposure in generated summaries or stored memory files.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- **CRM/Notes:** Pull prior client context from memory files or Obsidian
- **Financial data:** Reference AR aging, invoice history, budget files
- **Web research:** Use web_search for recent news on company/participants
- **Email:** Draft follow-up emails for Irfan's review (never send without approval)

---
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.