""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," LiteLLM maintainers said in an alert last week."
""An unauthenticated attacker could send a specially crafted Authorization header to any LLM API route and reach this query through the proxy's error-handling path.""
""Malicious activity fell into two phases driven by the same operator across two adjacent egress IPs, followed by a brief unauthenticated probe of the key-management endpoints," security researcher Michael Clark said."
A critical SQL injection vulnerability, CVE-2026-42208, in BerriAI's LiteLLM Python package has been exploited within 36 hours of its disclosure. The flaw allows unauthenticated attackers to modify the LiteLLM proxy database by sending crafted Authorization headers. The vulnerability affects versions prior to 1.83.7-stable, released on April 19, 2026. The first exploitation attempt occurred shortly after the GitHub advisory was published. Attackers targeted sensitive database tables, potentially gaining unauthorized access to credentials managed by the proxy.
Read at The Hacker News
Unable to calculate read time
Collection
[
|
...
]