Raw vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:NCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2026-44653 is a medium-severity Insertion of Sensitive Information Into Sent Data (CWE-201) vulnerability in Librechat Librechat. Its CVSS base score is 6.5 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Network Sniffing (T1040); ranked at the 19th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as LLM Application Platforms; in the Privacy and Disclosure risk domain.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and AC-4 (Information Flow Enforcement) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-34047
Vulnerability Data
LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, users with only `VIEW` access to an MCP server can retrieve the server's decrypted admin-managed secrets through `GET /api/mcp/servers` and `GET /api/mcp/servers/:serverName`.…
more
The returned config includes plaintext values for `apiKey.key` and `oauth.client_secret`. This allows viewers of a shared MCP server to exfiltrate the underlying provider credentials. Version 0.8..4 contains a patch. Other remediations include: never returning decrypted admin-managed secrets to non-owners; redacting apiKey.key and oauth.client_secret from all API responses consider returning only boolean presence indicators for secrets, similar to the auth-values route pattern; and, if owners need to edit configs without re-entering secrets, preserving secrets server-side and returning placeholders instead of plaintext.
- CWE(s)
AI Security AnalysisAI
- AI Category
- LLM Application Platforms
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, chatgpt, librechat, mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 1 hardening rule · 1 OS baseline
V14.2.3
Mitigating Controls (NIST 800-53 r5) AI
Directly enforces policy-based information flow rules that block transmission of sensitive data to unauthorized actors.
Enforces authorizations on logical access so that sensitive data is not released to unauthorized recipients.
Requires validation of outbound information to ensure sensitive content is not disclosed in responses or messages.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly prevent insertion of sensitive data into application outputs and messages.
Monitoring runtime data flows and outputs can detect sensitive data being transmitted.
Protecting data-in-transit can include filtering or encrypting to avoid exposing sensitive content.
Protecting data-in-use includes removing confidential values before they are processed or sent.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Data-masking techniques can prevent sensitive values from appearing in transmitted payloads.
Classification identifies sensitive data so it is not inadvertently transmitted.
Labelling makes sensitive data visible to developers and prevents accidental inclusion in outbound messages.
Information-transfer rules directly govern what data may be sent to external parties.
PII-protection requirements reduce the chance of sending personal data to unauthorized recipients.
DLP controls inspect and block outbound flows that contain sensitive information.