# CVE-2026-89032: BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer

> Authenticated users can bypass tenant isolation in the semantic cache to read other tenants' data and trigger unauthorized tool execution.

- **Severity:** High 8.7 (`CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N`)
- **Exploited in the wild:** Not known
- **Login needed:** Any signed-in user
- **Attackable:** Over the internet
- **Victim action needed:** A user has to click or open something
- **Fix available:** Yes
- **Published:** 25 Sep 2026
- **Updated:** 1 Oct 2026
- **Also known as:** GHSA-237m-2qxv-ww7c, MINI-2c5f-pjh9-qf82, MINI-2xh9-wvgc-xrf2, MINI-4m6h-r6g6-4q42, MINI-c26q-7f7f-xgv2, MINI-cfpf-3xcf-mq5g, MINI-fg68-758j-xrr8, MINI-fwww-wmrr-rmw7, MINI-q7f8-f9h7-pwj5, MINI-vg4f-w2f5-hw43, MINI-vm36-74x6-wqp3, MINI-vwj8-cr58-fq62, MINI-xcfv-v8v7-6p6w

## What is CVE-2026-89032?

CVE-2026-89032 is a high-severity missing authorization vulnerability in BerriAI litellm, published on 25 Sep 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.

### Official description

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants' personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.

Weakness: CWE-863 (Incorrect Authorization)

## Which versions are affected by CVE-2026-89032?


## How do I fix CVE-2026-89032?

Upgrade to a fixed version.

## Is CVE-2026-89032 being exploited?

There is no known exploitation of CVE-2026-89032 in the wild and no public exploit code.

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-89032 and fix it if it is affected.

What it is: CVE-2026-89032 is a high-severity missing authorization vulnerability in BerriAI litellm, published on 25 Sep 2026. Any signed-in user can exploit it over the network, and only if a user opens a file or follows a link.
Exploitation: There is no known exploitation of CVE-2026-89032 in the wild and no public exploit code.

Affected product: BerriAI litellm. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-89032/ (Markdown: https://insights.sbomify.com/CVE-2026-89032/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-89032
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-89032
- OSV: https://osv.dev/vulnerability/CVE-2026-89032

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-89032/
Summaries are generated and may contain mistakes; the official description above is the record.