Security readout for executives and security teams
Plain-English summary
CVE-2026-30623 is a critical remote code execution issue in LiteLLM 1.18.10 MCP server creation. A malicious configuration can cause the host to run operating system commands with LiteLLM’s privileges. This can affect confidentiality, integrity, and availability if the feature is reachable by an attacker.
Executive priority
Treat this as urgent for any exposed LiteLLM deployment using MCP server creation. The impact is full host compromise under the LiteLLM process, but urgency depends on whether the vulnerable feature is enabled and reachable.
Technical view
The CVE describes CWE-77 command injection in LiteLLM MCP server creation. JSON configuration accepts arbitrary command and args values and executes them without validation. CVSS 3.1 is 9.8 with network attack vector, low complexity, no privileges, no user interaction, and high CIA impact.
Likely exposure
Exposure is most likely where LiteLLM 1.18.10 is deployed and MCP server creation accepts untrusted or externally reachable input. The source bundle lists affected vendor/product metadata as unavailable, so teams should confirm actual LiteLLM versions and MCP enablement locally.
Exploitation context
The bundle does not show KEV listing or cited evidence of active exploitation. The CVSS vector indicates remote, unauthenticated, no-interaction exploitability, but the exact exposed route, authentication model, and deployment prerequisites are not described in the provided sources.
Researcher notes
Evidence supports command injection/RCE through MCP stdio configuration handling. Public bundle data lacks CPEs, complete affected-version range, patch version, and exploit-in-the-wild confirmation. Avoid assuming broader LiteLLM versions are affected without vendor confirmation.
Mitigation direction
- Check LiteLLM’s advisory for patched versions or vendor-recommended remediation.
- Disable MCP server creation if it is not operationally required.
- Restrict MCP configuration changes to trusted administrators only.
- Block external access to LiteLLM management surfaces where possible.
- Run LiteLLM with least-privilege service accounts and host isolation.
- Review existing MCP server configurations for unexpected command or args values.
Validation and detection
- Inventory LiteLLM deployments and confirm whether version 1.18.10 is present.
- Determine whether MCP server creation is enabled in each deployment.
- Verify who can submit or modify MCP JSON configuration.
- Review logs for unexpected MCP server creation or command execution events.
- Confirm remediation against current LiteLLM vendor guidance.
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-77: Command execution behavior lookup
Command injection weaknesses can lead defenders to review execution techniques and command interpreter telemetry. 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 lookupExecution behavior lookup
The CVE wording references code or command execution, so execution technique review may help defensive triage. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2026-30623 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
- Critical
- CVSS
- 9.8 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
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.
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:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H3.95.9CISA-ADPVulnerability scoring details
Base CVSS 3.1 score
9.8CriticalVector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
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.
- CVE updatedCVE Program
The CVE record metadata indicates this as the latest update time.
ADP provider summaries
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/BerriAI/litellmCVE reference, mitre
- https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/CVE reference, mitre
- https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026CVE reference, mitre
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 Neutralization of Special Elements used in a Command ('Command Injection')
Improper Neutralization of Special Elements used in a Command ('Command Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.