CVE-2025-34072

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.

CVSS

No CVSS.

References

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

Configurations

No configuration.

History

03 Jul 2025, 15:13

Type	Values Removed	Values Added
New CVE

Information

Published : 2025-07-02 14:15

Updated : 2025-07-03 15:13

NVD link : CVE-2025-34072

Mitre link : CVE-2025-34072

CVE.ORG link : CVE-2025-34072

JSON object : View

Products Affected

No product.

CWE

CWE-20

Improper Input Validation

CWE-200

Exposure of Sensitive Information to an Unauthorized Actor

{"id": "CVE-2025-34072", "cveTags": [], "metrics": {"cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 9.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "valueDensity": "NOT_DEFINED", "vectorString": "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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "NONE", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "NONE", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "vulnConfidentialityImpact": "HIGH", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "published": "2025-07-02T14:15:24.817", "references": [{"url": "https://embracethered.com/blog/posts/2025/security-advisory-anthropic-slack-mcp-server-data-leakage/", "source": "disclosure@vulncheck.com"}, {"url": "https://vulncheck.com/advisories/anthropic-slack-mcp-server-data-exfiltration", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Awaiting Analysis", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-20"}, {"lang": "en", "value": "CWE-200"}]}], "descriptions": [{"lang": "en", "value": "A data exfiltration vulnerability exists in Anthropic\u2019s 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\u2019s 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."}, {"lang": "es", "value": "Existe una vulnerabilidad de exfiltraci\u00f3n de datos en el servidor obsoleto del Protocolo de Contexto de Modelo (MCP) de Slack de Anthropic mediante el despliegue autom\u00e1tico de enlaces. Cuando un agente de IA que utiliza el servidor MCP de Slack procesa datos no confiables, estos pueden manipularse para generar mensajes con hiperv\u00ednculos manipulados por el atacante que integran datos confidenciales. Los bots de previsualizaci\u00f3n de enlaces de Slack (p. ej., Slack-LinkExpanding, Slackbot, Slack-ImgProxy) emiten solicitudes salientes a la URL controlada por el atacante, lo que resulta en la exfiltraci\u00f3n de datos privados sin necesidad de hacer clic."}], "lastModified": "2025-07-03T15:13:53.147", "sourceIdentifier": "disclosure@vulncheck.com"}