Data Exfiltration Vulnerability in Anthropic's Slack Model Context Protocol Server
CVE-2025-34072

9.3CRITICAL

Key Information:

Vendor

Anthropic

Status
Slack Mcp Server
Vendor
CVE Published:
2 July 2025

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2025-34072?

A vulnerability has been identified in Anthropic's deprecated Slack Model Context Protocol (MCP) Server that allows data exfiltration through automatic link unfurling. When an AI agent processes untrusted data, it can be exploited to generate messages that include malicious hyperlinks designed to extract sensitive data. The Slack link preview bots automatically make outbound requests to these attacker-controlled URLs, leading to unintended private data leakage without any user interaction.

Affected Version(s)

Slack MCP Server 0

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2025-34072 - Proof of Concept

References

https://embracethered.com/blog/posts/2025/security-adviso...
third-party-advisorytechnical-descriptionexploit
https://vulncheck.com/advisories/anthropic-slack-mcp-serv...
third-party-advisory

CVSS V4

Score:
9.3
Severity:
CRITICAL
Confidentiality:
High
Integrity:
None
Availability:
None
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

wunderwuzzi of Embrace The Red
.
CVE-2025-34072 : Data Exfiltration Vulnerability in Anthropic's Slack Model Context Protocol Server