CVE-2025-34072 — UNKNOWN AI Security Vulnerability

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes...

Full analysis pending. Showing NVD description excerpt.

Severity & Risk

CVSS 3.1

N/A

EPSS

N/A

KEV Status

Not in KEV

Sophistication

N/A

Recommended Action

No patch available

Monitor for updates. Consider compensating controls or temporary mitigations.

Compliance Impact

Compliance analysis pending. Sign in for full compliance mapping when available.

Technical Details

NVD Description

A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing attacker-crafted hyperlinks embedding sensitive data. Slack’s link preview bots (e.g., Slack-LinkExpanding, Slackbot, Slack-ImgProxy) will then issue outbound requests to the attacker-controlled URL, resulting in zero-click exfiltration of private data.

Weaknesses (CWE)

CWE-20 CWE-200

References

Timeline

Published

July 2, 2025

Last Modified

July 3, 2025

First Seen

July 2, 2025