CVE-2025-34072
Published: 02 July 2025
Summary
CVE-2025-34072 is a critical-severity Improper Input Validation (CWE-20) vulnerability in Embracethered (inferred from references). Its CVSS base score is 9.3 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Messaging Applications (T1213.005); ranked in the top 39.3% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Privacy and Disclosure risk domain; MITRE ATLAS techniques in scope: LLM Prompt Injection (AML.T0051).
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-19718
Vulnerability details
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- Classification Reason
- Matched keywords: ai, anthropic, mcp, model context protocol
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability enables collection from Slack messaging applications (T1213.005) by manipulating the AI agent to embed private Slack data in attacker-crafted hyperlinks within generated messages. Slack bots then automatically fetch these hyperlinks, resulting in zero-click exfiltration over web service (T1567) to the attacker-controlled URL.
MITRE ATLAS TechniquesAI
MITRE ATLAS techniques
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Automated marking applies security attributes to system outputs, making it harder for attackers to exploit unmarked sensitive information leading to unauthorized exposure.
Proper attribute retention and permitted-value enforcement limits unauthorized actors from accessing sensitive information lacking correct labels.
Prevents unauthorized exposure of sensitive information by prohibiting untrusted external systems from processing or storing it.
By enforcing authorization matching prior to sharing, the control reduces the risk of exposing sensitive information to unauthorized actors.
Review and removal of nonpublic information from publicly accessible systems directly prevents exposure of sensitive data to unauthorized actors.
Data mining protection mechanisms detect and block unauthorized bulk extraction of sensitive data, directly mitigating exposure to unauthorized actors.
Literacy training teaches users to recognize and avoid actions that result in unauthorized exposure of sensitive information.
Retaining and monitoring training records confirms personnel have completed privacy and security awareness training on handling sensitive data, reducing the chance of unauthorized exposure due to lack of knowledge.