PYSEC-2026-1547 LiteLLM Server-Side Request Forgery (SSRF) vulnerability

A Server-Side Request Forgery SSRF vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the apibase parameter when making requests to POST /chat/completions, causing the application to send the request to the domain specified by apibase. This request...

PT-2026-56268

Name of the Vulnerable Software and Affected Versions mem0 affected versions not specified Description Unauthenticated config API endpoints expose LLM API keys in plaintext and enable server-side request forgery SSRF, a technique where an attacker induces the server to make requests to an...

CVE-2026-55514 vLLM denial of service via prompt embeds on M-RoPE models

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

CVE-2026-54234 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then convert...

LiteLLM 1.74.2 < 1.83.7 Command Injection Vulnerability (GHSA-v4p8-mg3p-g94g)

The version of the LiteLLM Python package installed on the remote host is 1.74.2 before 1.83.7. It is, therefore, affected by a vulnerability: - From version 1.74.2 to before version 1.83.7, two endpoints used to preview an MCP server before saving it — POST /mcp-rest/test/connection and POST...

PYSEC-2026-400 llm CLI tool contains a code injection vulnerability via `--functions` command-line argument

The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec function...

PYSEC-2026-390 LiteLLM: Authentication bypass via OIDC userinfo cache key collision

Impact When JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20 characters. This configuration option is not enabled by default. Most instances are not affected. A...

PYSEC-2026-562 vanna vulnerable to remote code execution caused by prompt injection

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

CVE-2026-47102

A flaw was found in LiteLLM. A user with access to the /user/update endpoint can exploit a privilege escalation vulnerability. By modifying their own userrole to proxyadmin, an attacker can gain full administrative access to LiteLLM, including control over all users, teams, keys, models, and prom...

CVE-2026-45792

Vulnerability summary (CVE-2026-45792) RTK (Rust Token Killer) prior to 0.32.0 trusts project-local configuration by auto-loading the highest-priority .rtk/filters.toml without user notification. An attacker with repository access can place a malicious filter to modify shell command output before...

CVE-2026-54235

vLLM is an inference and serving engine for large language models LLMs. Prior to 0.23.1rc0, ll temperature validation gates use comparison operators , which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagat...

CVE-2026-49468

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

EUVD-2026-38366

Crawl4AI before 0.8.7 contains a server-side request forgery vulnerability in the /crawl, /crawl/stream, /md, and /llm endpoints that fetch arbitrary user-supplied URLs without validation. Unauthenticated attackers can bypass the internal-address blocklist using IPv6-mapped IPv4 addresses to reac...

CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

CVE-2026-49468

LiteLLM is a proxy server (AI Gateway) for calling LLM APIs. A host-header parsing flaw could allow authentication bypass by making the auth gate evaluate a different route than dispatched, effectively bypassing access controls under specific conditions. The issue is mitigated by upgrading to 1.8...

LangGenius, Inc. Dify has an SSRF vulnerability (CNVD-C-2026-287908)

Dify is an open-source LLM application development platform. LangGenius, Inc. Dify has an SSRF vulnerability, which allows attackers to obtain sensitive information...

Exploit for SQL Injection in Litellm

CVE-2026-42208 — LiteLLM Pre-Auth SQL Injection Lab A local l...

PT-2026-50481

Name of the Vulnerable Software and Affected Versions Open-webui affected versions not specified Description An authenticated user can access files belonging to other users by exploiting a lack of ownership verification in the image processing path. When the POST endpoint "/api/chat/completions"...

Server-side Request Forgery (SSRF)

Overview Crawl4AI is a 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the baseurl parameter in API requests and the resolution of environment variables in the LLM configuration process. An attack...