LiveActive security incident?Get immediate response
CVE Record

CVE-2026-42203: LiteLLM: Server-Side Template Injection in /prompts/test endpoint

LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.80.5 to before version 1.83.7, the POST /prompts/test endpoint accepted user-supplied prompt templates and rendered them without sandboxing. A crafted template could run arbitrary code inside the LiteLLM Proxy process. The endpoint only checks that the caller presents a valid proxy API key, so any authenticated user could reach it. Depending on how the proxy is deployed, this could expose secrets in the process environment (such as provider API keys or database credentials) and allow commands to be run on the host. This issue has been patched in version 1.83.7.

HighCVSS 8.8Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

LiteLLM Proxy versions 1.80.5 through before 1.83.7 could let any valid proxy API key holder run unsafe prompt templates. In practical terms, a normal authenticated user might execute code inside the proxy process, potentially exposing API keys, database credentials, or host access depending on deployment.

Executive priority

Treat this as urgent for any production LiteLLM Proxy because compromise could expose LLM provider keys and infrastructure secrets. Prioritize upgrade and key review before expanding user access.

Technical view

The POST /prompts/test endpoint rendered user-supplied prompt templates without sandboxing, causing server-side template injection and possible arbitrary code execution in the LiteLLM Proxy process. The issue is authenticated, network-reachable, low-complexity, and patched in 1.83.7.

Likely exposure

Exposure is limited to LiteLLM Proxy deployments running versions >=1.80.5 and <1.83.7 where users or services have valid proxy API keys. Risk increases if the proxy stores provider keys, database credentials, or other secrets in process environment variables.

Exploitation context

The source bundle does not show CISA KEV listing or cited evidence of active exploitation. The vulnerability is still serious because exploitation requires only a valid proxy API key and no user interaction.

Researcher notes

Mapped weaknesses are CWE-1336 and CWE-94. CVSS 8.8 reflects AV:N, AC:L, PR:L, UI:N with high confidentiality, integrity, and availability impact. Evidence supports authenticated code execution risk, but not public exploitation status.

Mitigation direction

  • Upgrade LiteLLM to version 1.83.7 or later.
  • Review vendor advisory and release notes for any deployment-specific guidance.
  • Restrict proxy API keys to trusted users and services only.
  • Audit and rotate secrets if /prompts/test usage looks suspicious.
  • Limit network access to the LiteLLM Proxy where operationally possible.

Validation and detection

  • Inventory LiteLLM Proxy versions across all environments.
  • Confirm no running deployment is between 1.80.5 and 1.83.6.
  • Review access logs for POST requests to /prompts/test.
  • Check which users or services hold valid proxy API keys.
  • Verify upgraded instances report version 1.83.7 or later.
Prepared
Confidence
high
Sources
7

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

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 · low confidence lookup

CWE-1336: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. 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 lookup
cwe · medium confidence lookup

CWE-94: Code execution behavior lookup

Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process 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 lookup
description · low confidence lookup

Execution 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 lookup
description · low confidence lookup

Database behavior lookup

The CVE wording references database injection or access, so collection and exfiltration review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-42203 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
High
CVSS
8.8 (3.1)
Known Exploited
No
Published

Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Official CVE source material

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.

2CVSS vectors
5Timeline events
2ADP providers
6Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: total

CVSS vector scores

2 official scores

We 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.

ScoreVersionSeverityVectorExploitImpactSource
8.8CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H2.85.9redhat-SADP
8.6CVSS 4.0HighCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N——GitHub_M

Vulnerability scoring details

Base CVSS 4.0 score

8.6High
CVSS 4.0 vector shape for CVE-2026-42203Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:N/SC:N/SI:N/SA:N

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
redhat-SADPlitellm: LiteLLM: Arbitrary code execution via unsandboxed prompt templates
other:Red Hat severity ratingcvssV3_1
  • 2026-05-08T04:01:50.142Z: Reported to Red Hat.
  • 2026-05-08T03:36:58.648Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
BerriAIlitellm>= 1.80.5, < 1.83.7Listed
Weakness

CWE details

CWE-1336CWE-94

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.