CVE-2025-34072 Anthropic Slack MCP Server Data Exfiltration via Link Unfurling
Attackers can exfiltrate sensitive data via crafted links in AI agent messages, triggering Slack's link preview bots to send data to attacker-controlled servers.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2025-34072?
CVE-2025-34072 is a critical vulnerability in Anthropic Slack MCP Server, published on 2 Jul 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Which versions are affected by CVE-2025-34072?
How do I fix CVE-2025-34072?
No fix has been published for CVE-2025-34072 yet. Limit exposure of the affected software until one is available.
Is CVE-2025-34072 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2025-34072 exists.
Sources
Also known as GHSA-gmx5-crwh-6vxg.