CVE-2026-37004: Security vulnerability
CVE-2026-37004 affects LiteLLM. The published description indicates a remote or untrusted-network exploitation path.
What happened
CVE-2026-37004: BerriAI litellm 82 4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS. 4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotprompt_content parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2. A security weakness in LiteLLM is being tracked as CVE-2026-37004.
CVE-2026-37004 affects LiteLLM. CVE-2026-37004 currently carries a CRITICAL 9 8 severity signal in the retained vulnerability data. The important point is that running an affected version of LiteLLM creates exposure, while an actual compromise still depends on whether the attacker can reach the trigger conditions described above.
The published description indicates a remote or untrusted-network exploitation path. The available description indicates that the vulnerable path can be reached remotely or from an untrusted network, so the exposure of LiteLLM becomes part of the attack condition. No exploitation flag is present in the retained CyberDeltaForce data at this time; that status can change as vendor and threat-intelligence reporting develops.
Editorial note: this News Brief follows the available evidence and adds length only when additional facts or useful context are available. Where public reporting does not establish a specific victim sequence, CyberDeltaForce does not present one as fact.
What the reporting and advisory establish
4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotprompt_content parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.
CVE-2026-37004 currently carries a CRITICAL 9.8 severity signal in the retained vulnerability data.
No exploitation flag is present in the retained CyberDeltaForce data at this time; that status can change as vendor and threat-intelligence reporting develops.
CVE-2026-37004: BerriAI litellm <=1.82.4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS
A security weakness in LiteLLM is being tracked as CVE-2026-37004. The available description indicates that the vulnerable path can be reached remotely or from an untrusted network, so the exposure of LiteLLM becomes part of the attack condition. The issue currently carries a CRITICAL 9.8 severity signal in the available reporting. There is no reported exploitation in the current available reporting, so the public picture at this point is a disclosed vulnerability with known exploitation conditions rather than a confirmed compromise of every affected installation. The important point is that running an affected version of LiteLLM creates exposure, while an actual compromise still depends on whether the attacker can reach the trigger conditions described above. 4 is vulnerable to Server-Side Template Injection (SSTI), which allows unauthenticated remote attackers to execute arbitrary OS commands via a crafted dotprompt_content parameter in the /prompts/test endpoint due to use of an unsandboxed jinja2.
What this means for your environment
Move from the published facts to the technical path, exposure conditions and defensive decisions that matter in a real environment.
Attack & Exploitation Path
The sequence below shows how the vulnerability can be reached and what successful exploitation can produce. Each stage is labeled by evidence status.
Required condition: an affected LiteLLM instance is reachable from a network position available to the attacker.
attacker-controlled network input reaches the vulnerable function on the affected LiteLLM service.
Not publicly disclosed in enough technical detail to describe the mechanism without inference.
Not publicly disclosed in enough detail to state a specific post-exploitation result without inference.
Identify remotely reachable LiteLLM; remove unnecessary exposure; apply the vendor fix or mitigation; then review service, network and identity telemetry for exploitation attempts or unexpected follow-on activity.
Why this matters to you
CVE-2026-37004 matters because the practical risk is not the score alone — it is whether LiteLLM exists in your environment and whether the reported trigger or exposure path can reach it. The current severity is CRITICAL 9.8. No exploitation flag is currently present in the CDF data, but that does not remove the need to validate affected systems.
Does this deserve attention in my environment?
Check the conditions below against your use of LiteLLM.
Select the conditions that are true in your environment. Leaving a condition unselected does not mean you are safe — it only means you have not marked it as applicable.
- Search endpoint, software and asset inventory for LiteLLM.
- Confirm the vendor-recommended fixed version or mitigation and verify deployment, not just assignment, across affected assets.
- Review relevant endpoint, application, network or identity telemetry for activity associated with exploitation of the affected component.
- Track vendor and government guidance for any change in exploitation status while remediation is underway.
What remains unconfirmed
- Available reporting does not currently indicate exploitation, but that can change as vendor, government or threat-intelligence reporting develops.
Sources & References
Original reporting and technical references are kept here for readers who want to verify the facts. Publisher names stay out of the reading flow above.