CriticalVulnerabilityLLM-specific
CVE-2026-37004: LiteLLM unauthenticated command execution via template injection
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-37004
- Published
- Record updated
- Affected
- litellm < 1.83.7
- Fixed in
- 1.83.7
- released April 13, 2026, 136 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.8%
Summary
BerriAI litellm versions up to and including 1.82.4 are vulnerable to Server-Side Template Injection (CVE-2026-37004). Unauthenticated remote attackers can execute arbitrary OS commands by sending a crafted dotprompt_content parameter to the /prompts/test endpoint, because the code uses an unsandboxed jinja2.Environment.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
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
- MediumFake OpenAI, SpaceX events used to steal Microsoft, Google accountsSimilar attack · BleepingComputer
- HighGHSA-64vx-6h2c-rjh7: Banks: Unsafe importlib.import_module of attacker-controlled Tool.import_path in CompletionExtension allows RCESimilar attack · GitHub Advisory Database
- MediumHacking on Autopilot: Inside ARTEX Cybercrime CampaignsSimilar attack · Check Point Research
- MediumCVE-2026-122160: myshell-ai AIlice HuggingFace Model Wrapper untrusted model loadingSimilar attack · NVD/CVE Database
- MediumCVE-2026-122159: Edge0-AI Audio8_TTS path traversal via slow_decode_models argumentSimilar attack · NVD/CVE Database