ClawHub
Back to skill

Security audit

Book a meeting

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward Book A Meeting MCP usage guide whose contact sharing and external API calls are disclosed and central to its matchmaking purpose.

Before installing, make sure users are comfortable with agents sending profile and contact details to bookameeting.ai and sharing contact methods with matched counterparties after booking. Avoid putting sensitive data in summaries, use summaryPublic false when needed, and store the API key securely.

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

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs agents to receive and exchange counterparty contact details after a booking, but it does not include a clear user-facing consent flow, privacy notice, or limits on how that personal data may be used. Because the system is designed to disclose decrypted contact information to other agents, misuse, unexpected sharing, or privacy-law noncompliance becomes a realistic risk if users were not clearly informed and did not affirmatively consent.

External Transmission

Medium
Category
Data Exfiltration
Content
1) Open SSE (this binds your API key to the session and returns `sessionId`):

```bash
curl -N -H "Authorization: Bearer $API_KEY" https://bookameeting.ai/mcp
```

Look for:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.