CVE-2026-45019

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For sse and streamable-http transports, ConnectSseMCPRequest and ConnectStreamableHttpMCPRequest in backend/chainlit/types.py accept a user-controlled url and optional headers dictionary without scheme validation, private-address filtering, or an allowlist. The connect_mcp handler in backend/chainlit/server.py passes these values to sse_client() or streamablehttp_client(), allowing the Chainlit server to make blind outbound requests to arbitrary internal or external services, including cloud metadata endpoints, with attacker-controlled Authorization and Cookie headers. The SSE URL sink has existed since 2.4.0rc0, while attacker-controlled header forwarding and streamable-http support were added in 2.6.4. The response is consumed internally and not returned, but the attacker can issue state-changing authenticated requests, discover internal services, scan ports, and probe metadata endpoints. This issue is fixed in version 2.12.0.

CVSS v3 7.2 HIGH

7.2^/10

CVSS v3 : HIGH

Vector :

Exploitability : 3.9 / Impact : 2.7

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact LOW

Integrity Impact LOW

Availability Impact NONE

Scope CHANGED

References

Link	Resource
https://github.com/Chainlit/chainlit/blob/2.12.0/docs/security-advisory-2026-mcp.md#spl-2026-002--ssrf-via-mcp-streamable-http--sse
https://github.com/Chainlit/chainlit/commit/0565fd0eccb915fce159929598b053ed79f6e0c9
https://github.com/Chainlit/chainlit/releases/tag/2.12.0
https://github.com/Chainlit/chainlit/security/advisories/GHSA-hvfh-5mj3-5f3j

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-25 20:16

Updated : 2026-09-09 21:07

NVD link : CVE-2026-45019

Mitre link : CVE-2026-45019

CVE.ORG link : CVE-2026-45019

JSON object : View

Products Affected

No product.

CWE

CWE-918

Server-Side Request Forgery (SSRF)

{"id": "CVE-2026-45019", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-45019", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-08-27T13:54:59.266525Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 7.2, "attackVector": "NETWORK", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "NONE", "privilegesRequired": "NONE", "confidentialityImpact": "LOW"}, "impactScore": 2.7, "exploitabilityScore": 3.9}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "Chainlit", "product": "chainlit", "versions": [{"status": "affected", "version": ">= 2.4.0rc0, < 2.12.0"}]}]}], "published": "2026-08-25T20:16:55.910", "references": [{"url": "https://github.com/Chainlit/chainlit/blob/2.12.0/docs/security-advisory-2026-mcp.md#spl-2026-002--ssrf-via-mcp-streamable-http--sse", "source": "security-advisories@github.com"}, {"url": "https://github.com/Chainlit/chainlit/commit/0565fd0eccb915fce159929598b053ed79f6e0c9", "source": "security-advisories@github.com"}, {"url": "https://github.com/Chainlit/chainlit/releases/tag/2.12.0", "source": "security-advisories@github.com"}, {"url": "https://github.com/Chainlit/chainlit/security/advisories/GHSA-hvfh-5mj3-5f3j", "source": "security-advisories@github.com"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-918"}]}], "descriptions": [{"lang": "en", "value": "Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For sse and streamable-http transports, ConnectSseMCPRequest and ConnectStreamableHttpMCPRequest in backend/chainlit/types.py accept a user-controlled url and optional headers dictionary without scheme validation, private-address filtering, or an allowlist. The connect_mcp handler in backend/chainlit/server.py passes these values to sse_client() or streamablehttp_client(), allowing the Chainlit server to make blind outbound requests to arbitrary internal or external services, including cloud metadata endpoints, with attacker-controlled Authorization and Cookie headers. The SSE URL sink has existed since 2.4.0rc0, while attacker-controlled header forwarding and streamable-http support were added in 2.6.4. The response is consumed internally and not returned, but the attacker can issue state-changing authenticated requests, discover internal services, scan ports, and probe metadata endpoints. This issue is fixed in version 2.12.0."}], "lastModified": "2026-09-09T21:07:31.353", "sourceIdentifier": "security-advisories@github.com"}