GHSA-jjhc-v7c2-5hh6: LiteLLM: Authentication bypass via OIDC userinfo cache key collision
- Identifiers
- CVE-2026-35030GHSA-jjhc-v7c2-5hh6
- Published
- Record updated
- Affected
- litellm < 1.83.0
- Fixed in
- 1.83.0
- released March 31, 2026, 3 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.6%
Summary
LiteLLM's OIDC userinfo cache keys JWT tokens by their first 20 characters (`token[:20]`) when `enable_jwt_auth: true` is set. Because tokens from the same signing algorithm share identical leading characters, an unauthenticated attacker can craft a token that hits a legitimate user's cache entry and inherits that user's identity and permissions. The option is not enabled by default, so most instances are not affected.
Mitigation
Fixed in v1.83.0. The cache key now uses the full hash of the JWT token. Workaround: disable OIDC userinfo caching by setting the cache TTL to 0, or disable JWT authentication entirely.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- litellmPyPILLM dependency since 2023-07-27 · 55 tracked dependents
Related items
- InfoThreatsDay: GPT-6.2 Jailbreak Flaws, BubbleLoader PNG Malware, $500M Ransom Demands + 17 More StoriesSimilar attack · The Hacker News
- Info30 Years of Gatekeeper Asymmetry Doom: The Paradox that Makes Powerful LLMs More VulnerableSimilar attack · Check Point Research
- InfoJailbreak Detection on Large Language Models via Contrastive Prototype StructuresSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoIDEA: Intent-Dominance Evidence Audit for Inference-Time Backdoor Detection in GUI AgentsSimilar attack · Arxiv (cs.RO + cs.CV security)
- InfoDressed in Authority: Practical Black-Box Jailbreaking of MLLMs via Visual Trust BiasSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)