AI Sec Watch: A Security Intelligence Platform for AI Systems

Luu, T.J.

CriticalVulnerabilityLLM-specific

GHSA-46cm-pfwv-cgf8: LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

Source: GitHub Advisory(opens in a new tab)
Identifiers: CVE-2024-2952GHSA-46cm-pfwv-cgf8
Published: April 10, 2024
Record updated: October 10, 2026

View JSON

Affected: litellm < 1.34.42
Fixed in: 1.34.42
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 1.3%

Summary

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

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

CVSS score: 9.8(critical)
Patch available: Yes
CVSS vector: CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: none
EPSS: 1.3%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 10, 2026.
Disclosure date: April 10, 2024

Weaknesses and techniques

Weakness (CWE): CWE-76

Affected

Packages: litellm@< 1.34.42 (fixed: 1.34.42)

Classification

Attack type: Other
Attack sophistication: Moderate
AI component targeted: API
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative.

Original source: https://github.com/advisories/GHSA-46cm-pfwv-cgf8

First tracked: October 10, 2026 at 12:53 AM ET, from GitHub Advisory Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

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 · 54 tracked dependents

Summary

Mitigation

Affected packages in the Exposure Registry

Related items