Security Digest · Vulnerability record
CVE-2024-2952: LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint
BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the /completions endpoint.
CVSS 9.8 Critical EPSS 1.3% · p70
Should you act?
Critical and remotely reachable
No known exploitation yet, but it is network-reachable without credentials. This signal is computed from CISA KEV, EPSS and CVSS data; it is not an editorial verdict.
- Not in CISA KEV, but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 1.3%, percentile 70: FIRST’s model estimates a 1.3% chance of exploitation activity in the next 30 days, higher than 70% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes
litellm(PyPI) < 1.34.42, fixed in 1.34.42. Check your lockfile, including transitive dependencies.
What it is
BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious tokenizerconfig.json files that execute arbitrary code on the server.
From the GitHub advisory
BerriAI/litellm is vulnerable to Server-Side Template Injection (SSTI) via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization. Attackers can exploit this by crafting malicious tokenizerconfig.json files that execute arbitrary code on the server.
Weakness type: CWE-76.
Product: litellm (PyPI) · Assigned by: @huntr_ai · Published: 2024-04-10
Affected and fixed versions
| Ecosystem | Package | Vulnerable | First fixed |
|---|---|---|---|
| PyPI | litellm | < 1.34.42 | 1.34.42 |
| Vendor | Product | Affected versions (per CVE record) |
|---|---|---|
| berriai | berriai/litellm | unspecified < 1.34.42 |
Severity scores
| Scored by | CVSS | Score | Vector |
|---|---|---|---|
| @huntr_ai | 3.0 | 9.8 Critical | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
- Attack vector: network (remotely reachable)
- Attack complexity: low
- Privileges required: none (no login)
- User interaction: none
- Scope: unchanged
CVSS measures how bad a flaw is if exploited, not how likely exploitation is. Read it next to the exploitation data below.
Exploitation and urgency
- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc, automatable yes, technical impact total.
- FIRST EPSS (model of 2026-10-21): 1.27% probability of exploitation activity in the next 30 days; percentile 70.
Timeline
- — CVE record published by @huntr_ai
- — GitHub-reviewed advisory GHSA-46cm-pfwv-cgf8 published (critical)
- — CVE record last updated
Sources and references
Original sources first. Version and fix details should always be confirmed against the vendor or project advisory.
Vulnerability records
- GitHub Advisory GHSA-46cm-pfwv-cgf8 github.com
- CVE.org record CVE-2024-2952 cve.org
- NVD entry CVE-2024-2952 nvd.nist.gov
Other references from the CVE record and advisory
- huntr.com huntr.com
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- github.com github.com
- pypi.org pypi.org