BerriAI

Vulnerability activity for BerriAI: what is being exploited, what was published lately, and when the next patch release is due.

All vendors Open in the dashboard

Last 30 days

CVEs: 1
Critical (CVSS 9+): 1
Exploited (CISA KEV): 0
With exploit code: 0

Last 90 days

CVEs: 3
Critical (CVSS 9+): 1
Exploited (CISA KEV): 1
With exploit code: 0

Last 365 days

CVEs: 6
Critical (CVSS 9+): 2
Exploited (CISA KEV): 3
With exploit code: 3

Exploited now

CVEs on CISA's known-exploited list, newest first. "Days to KEV" counts from the CVE's publication.

8.8HighSep 2, 2026BerriAI LiteLLM Auth bypass / access controlCVE-2026-59822BerriAI LiteLLM contains an improper authentication vulnerability in the MCP Streamable HTTP endpoint that could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.Added to KEV Sep 2, 2026Exploited
8.7HighJun 8, 2026BerriAI LiteLLM Code / command injectionCVE-2026-42271BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.Added to KEV Jun 8, 2026Exploited91% likelyExploit codeMetasploit · NucleiDetection
9.3CriticalMay 8, 2026BerriAI LiteLLM SQL injectionCVE-2026-42208BerriAI LiteLLM contains a SQL injection vulnerability that allows an attacker to read data from the proxy's database and potentially modify it, leading to unauthorized access to the proxy and the credentials it manages.Added to KEV May 8, 2026Exploited89% likelyExploit codeMetasploit · NucleiDetection

Recent

9.9CriticalOct 22, 2026BerriAI litellm Privilege escalationCVE-2026-114612### Summary An authenticated user with `internal_user` privileges can escalate to `proxy_admin` and achieve remote code execution. The proxy uses one encryption key for two purposes: sealing secrets at rest and minting session tokens. An attacker exploits this by requesting a new API key with a crafted metadata field containing a forged admin credential as the "secret" value. The proxy encrypts and returns this payload. When this value is then presented as a bearer token, the proxy decrypts it,
5.3MediumSep 16, 2026BerriAI litellm SSRFCVE-2026-59823LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.9, an authenticated LiteLLM Proxy caller with a valid virtual key can place api_base inside the user_config request body to bypass is_request_body_safe, which blocks top-level api_base and base_url bu
8.8HighSep 2, 2026BerriAI LiteLLM Auth bypass / access controlCVE-2026-59822BerriAI LiteLLM contains an improper authentication vulnerability in the MCP Streamable HTTP endpoint that could allow an unauthenticated attacker to establish an authenticated MCP session using an arbitrary Bearer token.Exploited
8.7HighJun 8, 2026BerriAI LiteLLM Code / command injectionCVE-2026-42271BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host.Exploited91% likelyExploit codeMetasploit · NucleiDetection
9.3CriticalMay 8, 2026BerriAI LiteLLM SQL injectionCVE-2026-42208BerriAI LiteLLM contains a SQL injection vulnerability that allows an attacker to read data from the proxy's database and potentially modify it, leading to unauthorized access to the proxy and the credentials it manages.Exploited89% likelyExploit codeMetasploit · NucleiDetection
8.7HighApr 6, 2026BerriAI litellm Auth bypass / access controlCVE-2026-35029(1) The LiteLLM proxy server and its configuration are affected. (2) An authenticated user gains the ability to modify proxy configuration and environment. (3) Update to version 1.83.0 or later to enforce admin role authorization on the /config/update endpoint.4% likelyExploit codeNucleiDetection

See every BerriAI entry on the dashboard.