CVE-2024-2952 | Server-Side Template Injection in BerriAI/litellm

Exp

BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the `/completions` endpoint. The vulnerability arises from the `hf_chat_template` method processing the `chat_template` parameter from the `tokenizer_config.json` file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious `tokenizer_config.json` files that execute arbitrary code on the server.

Published: 2024-04-10 Last update: 2025-07-15 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2024-2952 is rated High Exploit Risk (82.4/100): CVSS Critical severity, with medium exploitation likelihood (EPSS 1.43%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2024-2952

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2024-2952

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-03-16 1.45% 1.43% -0.02%
2 2025-11-21 2.64% 1.45% -1.19%
3 2025-11-18 — 2.64% —

Full EPSS history (17 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-2952

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.0 CRITICAL
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]

Weakness enumeration for CVE-2024-2952

GitHub Security Advisory for CVE-2024-2952

GHSA-46cm-pfwv-cgf8 · Severity: critical · Ecosystem: pip — LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

Affected software / configurations for CVE-2024-2952

Vendor Product Version Raw CPE
litellm litellm < 1.34.42 cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*

References for CVE-2024-2952

cvelogic Threat Intelligence