6 matches found
tbphp GPT-Load log information leakage vulnerability
Versions 1.4.11 and earlier of tbphp GPT-Load contain a log information leakage vulnerability. This flaw arises because the Gin Logger middleware records the original query string prior to extracting the AuthKey parameter. As a result, the client-side proxy key is stored in plaintext within conso...
LiteLLM has SQL Injection in Proxy API key verification
ImpactA database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route for example POST /chat/completions an...
PYSEC-2026-391 LiteLLM has SQL Injection in Proxy API key verification
Impact A database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route for example POST /chat/completions a...
curl: HTTPS proxy connection reuse lets one easy handle inherit another handle's mTLS-authenticated proxy session
Summary: libcurl can reuse an already mTLS-authenticated HTTPS proxy TLS connection for a different easy handle even when that second handle does not have the proxy private key required to establish the session itself. The issue happens because the HTTPS proxy connection reuse identity does not...
vulnerabilities handled in LiteLLM by BerriAI
BerriAI has addressed vulnerabilities in LiteLLM, specifically in versions 1.74.2 to 1.83.6. LiteLLM is a widely used proxy for managing APIs to a large number of LLM systems in a centralized manner. The first vulnerability involves an SQL injection in the proxy API key verification mechanism,...
LiteLLM has SQL Injection in Proxy API key verification
Impact A database query used during proxy API key checks mixed the caller-supplied key value into the query text instead of passing it as a separate parameter. An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route for example POST /chat/completions a...