Litellm: Security Vulnerabilities
A vulnerability was determined in BerriAI litellm up to 1.63.1. The impacted element is an unknown function of the file litellm/proxy/management_endpoints/key_management_endpoints.py of the component Admin Key Handler. This manipulation causes improper authorization. The attack can be initiated remotely. The exploit has been publicly disclosed and may be utilized. Patch name: 23781. It is recommended to apply a patch to fix this issue. The vendor was contacted early about this disclosure.
CVSS Score
2.1
EPSS Score
0.003
Published
2026-06-21
LiteLLM prior to 1.83.10 allows a user to modify their own user_role via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user who can reach this endpoint can set their role to proxy_admin, gaining full administrative access to LiteLLM including all users, teams, keys, models, and prompt history. Users with the org_admin role have legitimate access to this endpoint and can exploit this vulnerability without chaining any additional flaw.
CVSS Score
8.7
EPSS Score
0.007
Published
2026-05-21
LiteLLM prior to 1.83.14 allows an authenticated internal_user to create API keys with access to routes that their role does not permit. When generating a key, the allowed_routes field is stored without verifying that the specified routes fall within the user's own permissions. A key created with access to admin-only routes can then be used to reach those routes successfully, bypassing the role-based access controls that would otherwise block the request, enabling full privilege escalation from internal_user to proxy_admin.
CVSS Score
8.7
EPSS Score
0.007
Published
2026-05-21
CVE-2026-42271
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST /mcp-rest/test/tools/list — accepted a full server configuration in the request body, including the command, args, and env fields used by the stdio transport. When called with a stdio configuration, the endpoints attempted to connect, which spawned the supplied command as a subprocess on the proxy host with the privileges of the proxy process. The endpoints were gated only by a valid proxy API key, with no role check. Any authenticated user — including holders of low-privilege internal-user keys — could therefore run arbitrary commands on the host. This issue has been patched in version 1.83.7.
Known exploited
CVSS Score
8.7
EPSS Score
0.759
Published
2026-05-08
CVE-2026-42208
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From version 1.81.16 to before version 1.83.7, a database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route (for example POST /chat/completions) and reach this query through the proxy's error-handling path. An attacker could read data from the proxy's database and may be able to modify it, leading to unauthorised access to the proxy and the credentials it manages. This issue has been patched in version 1.83.7.
Known exploited
CVSS Score
9.3
EPSS Score
0.835
Published
2026-05-08
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.
CVSS Score
8.6
EPSS Score
0.004
Published
2026-05-08
LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test_custom_code URI.
CVSS Score
8.8
EPSS Score
0.011
Published
2026-04-10
CVE-2026-33634
Trivy is a security scanner. On March 19, 2026, a threat actor used compromised credentials to publish a malicious Trivy v0.69.4 release, force-push 76 of 77 version tags in `aquasecurity/trivy-action` to credential-stealing malware, and replace all 7 tags in `aquasecurity/setup-trivy` with malicious commits. This incident is a continuation of the supply chain attack that began in late February 2026. Following the initial disclosure on March 1, credential rotation was performed but was not atomic (not all credentials were revoked simultaneously). The attacker could have use a valid token to exfiltrate newly rotated secrets during the rotation window (which lasted a few days). This could have allowed the attacker to retain access and execute the March 19 attack. Affected components include the `aquasecurity/trivy` Go / Container image version 0.69.4, the `aquasecurity/trivy-action` GitHub Action versions 0.0.1 – 0.34.2 (76/77), and the`aquasecurity/setup-trivy` GitHub Action versions 0.2.0 – 0.2.6, prior to the recreation of 0.2.6 with a safe commit. Known safe versions include versions 0.69.2 and 0.69.3 of the Trivy binary, version 0.35.0 of trivy-action, and version 0.2.6 of setup-trivy. Additionally, take other mitigations to ensure the safety of secrets. If there is any possibility that a compromised version ran in one's environment, all secrets accessible to affected pipelines must be treated as exposed and rotated immediately. Check whether one's organization pulled or executed Trivy v0.69.4 from any source. Remove any affected artifacts immediately. Review all workflows using `aquasecurity/trivy-action` or `aquasecurity/setup-trivy`. Those who referenced a version tag rather than a full commit SHA should check workflow run logs from March 19–20, 2026 for signs of compromise. Look for repositories named `tpcp-docs` in one's GitHub organization. The presence of such a repository may indicate that the fallback exfiltration mechanism was triggered and secrets were successfully stolen. Pin GitHub Actions to full, immutable commit SHA hashes, don't use mutable version tags.
Known exploited
CVSS Score
9.4
EPSS Score
0.604
Published
2026-03-23
SQL Injection vulnerability in BerriAI LiteLLM before 1.81.0 allows attackers to execute arbitrary commands via the key parameter to the "/key/block" and "/key/unblock" API endpoints.
CVSS Score
5.4
EPSS Score
0.003
Published
2025-07-03
In berriai/litellm version v1.52.1, an issue in proxy_server.py causes the leakage of Langfuse API keys when an error occurs while parsing team settings. This vulnerability exposes sensitive information, including langfuse_secret and langfuse_public_key, which can provide full access to the Langfuse project storing all requests.
CVSS Score
7.5
EPSS Score
0.005
Published
2025-03-20