Security readout for executives and security teams
Plain-English summary
LiteLLM versions before 1.84.0 can let an internet-based attacker bypass authentication on the MCP Streamable HTTP endpoint. A fabricated authorization header may cause failed key validation to be replaced with an empty authenticated-user object, allowing access to connected MCP tools without a valid LiteLLM key.
Executive priority
Treat this as an urgent remediation because CISA reports known exploitation and vulnerable deployments may expose powerful MCP tooling without valid authentication. Prioritize internet-facing gateways and those connected to sensitive data or actions. Upgrade promptly, assess logs for possible prior access, and confirm connected-tool privileges are appropriately limited.
Technical view
The endpoint’s OAuth2 passthrough fallback mishandled failed LiteLLM key validation by creating an empty UserAPIKeyAuth object. This authentication and missing-authentication-control flaw is tracked as CWE-287 and CWE-306. It is remotely reachable, requires no privileges or user interaction, and is fixed in LiteLLM 1.84.0.
Likely exposure
Exposure applies to LiteLLM versions earlier than 1.84.0 where the MCP Streamable HTTP endpoint is enabled and reachable by an attacker. Internet-facing deployments and environments connecting LiteLLM to sensitive MCP tools warrant the fastest review. The supplied evidence does not establish whether every pre-1.84.0 configuration exposes this endpoint.
Exploitation context
CISA lists CVE-2026-59822 in its Known Exploited Vulnerabilities catalog, supporting active exploitation in the wild. The supplied sources do not establish exploitation scale, targeted organizations, observed attacker objectives, or whether public exploit code exists. CVSS 4.0 rates it 8.8 due primarily to remote, unauthenticated confidentiality impact.
Researcher notes
The security boundary fails during fallback handling rather than ordinary successful key validation. Review the patched authentication flow and commit for exact code-level behavior. Assessment should focus on endpoint reachability, affected version, OAuth2 passthrough configuration, connected tool capabilities, and evidence of invalid authorization attempts followed by MCP activity. Avoid assuming compromise solely from version presence.
Mitigation direction
- Upgrade LiteLLM to version 1.84.0 or later.
- Follow the GitHub security advisory and release guidance for deployment-specific remediation.
- Until upgraded, restrict untrusted network access to the MCP Streamable HTTP endpoint.
- Review credentials and connected MCP-tool permissions if unauthorized access is suspected.
Validation and detection
- Inventory LiteLLM deployments and confirm each installed version.
- Identify whether the MCP Streamable HTTP endpoint is enabled and externally reachable.
- Confirm production instances run version 1.84.0 or later.
- Review available access and tool-activity logs for suspicious unauthenticated requests.
- Verify connected MCP tools use least-privilege permissions after remediation.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-287: Credential and account abuse lookup
Authentication and credential weaknesses can make valid-account abuse and credential telemetry useful review starting points. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCWE-306: Credential and account abuse lookup
Authentication and credential weaknesses can make valid-account abuse and credential telemetry useful review starting points. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupCredential and access behavior lookup
The CVE wording references authentication or credential exposure, so valid-account and credential-access review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-59822 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- High
- CVSS
- 8.8 (4.0)
- Known Exploited
- Yes
- Published
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
CISA KEV status
SSVC decision data
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N——GitHub_MVulnerability scoring details
Base CVSS 4.0 score
8.8HighVector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:N/SC:N/SI:N/SA:N
Vulnerability timeline
Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.
- CVE reservedCVE Program
The CVE ID was reserved by the assigning CNA.
- CVE publishedCVE Program
The CVE record was published.
- Added to KEVCISA-ADP
CISA Known Exploited Vulnerabilities metadata lists this CVE as known exploited.
- ADP timelineCISA-ADP
CVE-2026-59822 added to CISA KEV
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
- 2026-09-02T00:00:00.000Z: CVE-2026-59822 added to CISA KEV
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/BerriAI/litellm/security/advisories/GHSA-7488-6r32-c95qCVE reference, GitHub_M · x_refsource_CONFIRM
- https://github.com/BerriAI/litellm/pull/26463CVE reference, GitHub_M · x_refsource_MISC
- https://github.com/BerriAI/litellm/commit/73869f0faf7d11ee21adcb5f91b8c33a340b6c2cCVE reference, GitHub_M · x_refsource_MISC
- https://github.com/BerriAI/litellm/releases/tag/v1.84.0CVE reference, GitHub_M · x_refsource_MISC
- https://www.wiz.io/blog/ai-infrastructure-honeypotCVE reference, CISA-ADP · third-party-advisory
- https://www.cisa.gov/known-exploited-vulnerabilities-catalog?field_cve=CVE-2026-59822CVE reference, CISA-ADP · government-resource
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Authentication
Improper Authentication represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.
Missing Authentication for Critical Function
Missing Authentication for Critical Function represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.