Similarity Is Not Validity: Defending LLM Semantic Caches against Poisoning

Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity between the incoming query and cached queries. This design enables cache poisoning: an attacker can cache a malicious...

SUSE CVE-2026-89032

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

Incorrect Authorization

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Incorrect Authorization via a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by...

CVE-2026-89032

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

CVE-2026-89032

A flaw was found in LiteLLM. Due to a metadata key mismatch in the semantic cache component, an authenticated remote attacker can bypass tenant isolation by submitting semantically similar queries. This issue leads to information disclosure, allowing unauthorized access to cached responses...

CVE-2026-89032

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

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

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

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

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

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

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

EUVD-2026-87147

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

CVE-2026-89032

BerriAI LiteLLM versions prior to 1.101.0-rc.1 are vulnerable to a tenant isolation bypass within the semantic cache layer . The flaw is caused by a metadata key mismatch between the _get_semantic_cache_tenant_scope() and _get_metadata_variable_name() functions. An authenticated remote attacker w...

PT-2026-98928

Name of the Vulnerable Software and Affected Versions BerriAI LiteLLM versions prior to 1.101.0-rc.1 Description A tenant isolation bypass exists in the semantic cache layer due to a metadata key mismatch between the get semantic cache tenant scope and get metadata variable name functions...

CVE-2026-89032: Incorrect Authorization

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 getsemanticcachetenantscope and getmetadatavariablename. Attackers...

Cache Leakage

Spring AI is vulnerable to cache leakage. The vulnerability is due to the context hash used in the Semantic Cache support to isolate cached responses between different system prompts, where the hash may not provide sufficient separation and attackers can cause cached responses from one context to...

Use of a Broken or Risky Cryptographic Algorithm

Overview Affected versions of this package are vulnerable to Use of a Broken or Risky Cryptographic Algorithm due to the extractContextHash logic in SemanticCacheAdvisor.java. An attacker can receive cached responses from an unrelated system prompt by sending requests whose prompts collide under...

CVE-2026-59308

In Spring AI's Semantic Cache support, the context hash used to isolate cached responses between different system prompts could allow cached responses to be shared across unrelated contexts. Affected versions: Spring AI: 2.0.0...

CVE-2026-59308

Spring AI 2.0.0 contains a vulnerability in its Semantic Cache support. The context hash mechanism, intended to isolate cached responses between different system prompts, is insufficient and could allow cached responses to be shared across unrelated contexts . This results in low confidentiality ...

CVE-2026-59308 Semantic Cache Cross-Tenant Isolation Bypass via SHA-256 Truncation

In Spring AI's Semantic Cache support, the context hash used to isolate cached responses between different system prompts could allow cached responses to be shared across unrelated contexts. Affected versions: Spring AI: 2.0.0...

EUVD-2026-63932

In Spring AI's Semantic Cache support, the context hash used to isolate cached responses between different system prompts could allow cached responses to be shared across unrelated contexts. Affected versions: Spring AI: 2.0.0...

CVE-2026-59308 Semantic Cache Cross-Tenant Isolation Bypass via SHA-256 Truncation

In Spring AI's Semantic Cache support, the context hash used to isolate cached responses between different system prompts could allow cached responses to be shared across unrelated contexts. Affected versions: Spring AI: 2.0.0...