LiteLLMGHSA-46cm-pfwv-cgf8
LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint
Critical9.8CVE-2024-2952 · Published Apr 10, 2024 · updated Sep 10, 2026
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.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| litellm PyPI | < 1.34.42 | 1.34.42 |
Details and references
- CVSS 3.0
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- Severity from
- GitHub (reviewed advisory)
- Weakness
- CWE-76
- Also known as
- CVE-2024-2952, PYSEC-2026-387
- nvd.nist.gov/vuln/detail/CVE-2024-2952
- github.com/BerriAI/litellm/issues/2949
- github.com/BerriAI/litellm/pull/2941
- github.com/BerriAI/litellm/commit/8a1cdc901708b07b7ff4eca20f9cb0f1f0e8d0b3
- github.com/BerriAI/litellm
- github.com/BerriAI/litellm/blob/0d803e13798db40aa7463e64a6bafaee386424f5/litellm/proxy/proxy_server.py#L2087
- github.com/advisories/GHSA-46cm-pfwv-cgf8
- github.com/pypa/advisory-database/tree/main/vulns/litellm/PYSEC-2026-387.yaml
- huntr.com/bounties/a9e0a164-6de0-43a4-a640-0cbfb54220a4
- pypi.org/project/litellm
More LiteLLM advisories
All LiteLLM| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Jun 272024 | litellm vulnerable to improper access control in team management Medium5.3Jun 27, 2024 | Medium5.3 | 1.40.15 |
| Jun 272024 | litellm vulnerable to remote code execution based on using eval unsafelyCritical9.8Jun 27, 2024 | Critical9.8 | 1.40.16 |
| Jun 62024 | SQL injection in litellmMedium6.4Jun 6, 2024 | Medium6.4 | 1.40.0 |
| Jun 62024 | SQL injection in litellmMedium4.9Jun 6, 2024 | Medium4.9 | No fix yet |
| Jun 62024 | Arbitrary file deletion in litellmHigh6.5Jun 6, 2024 | High6.5 | 1.35.36 |
| May 182024 | litellm passes untrusted data to `eval` function without sanitizationHigh7.2May 18, 2024 | High7.2 | No fix yet |