ChatGPT AgentForger Flaw Could Deploy Rogue Workspace Agents via a Phishing Link
Cybersecurity researchers at Zenity Labs have disclosed a critical vulnerability in OpenAI's ChatGPT Workspace Agents, codenamed AgentForger, that could allow a single…
Tag: LiteLLM
CVE-2024-6587: Critical LiteLLM Vulnerability Exploited in AI Infrastructure Attacks
A critical vulnerability in LiteLLM that is being actively exploited by attackers to hijack AI infrastructure and conduct attacks against third parties.
LiteLLM Vulnerability Chain Enables Full Server Takeover by Low-Privilege Users
A chain of three vulnerabilities in LiteLLM, a widely deployed open-source AI gateway, allows low-privilege users to escalate to full admin and…
BerriAI Patches Critical LiteLLM Vulnerabilities
BerriAI, the maintainer of LiteLLM, released fixes in version 1.83.14-stable to address a chain of three critical vulnerabilities that could lead to…
X41 D-Sec Discovers LiteLLM Sandbox Escape Path
X41 D-Sec independently found a sandbox escape path in LiteLLM's Custom Code Guardrail playground endpoint, which bypassed a regex deny-list through runtime…
LiteLLM — Cybersecurity product profile
LiteLLM was identified as a relevant cybersecurity entity in recently ingested reporting. This profile is generated so related cyber news, CVEs, malware,…
Obsidian Security Discovers Critical LiteLLM Vulnerabilities
Obsidian Security, a cybersecurity company, disclosed a chain of three critical vulnerabilities in LiteLLM that allow low-privilege users to take over AI…
LiteLLM Authorization Bypass via Allowed Routes
CVE-2026-47101 is an authorization bypass vulnerability in LiteLLM where the allowed_routes field is not validated against user roles, allowing low-privilege users to…
LiteLLM Privilege Escalation via User Update Endpoint
CVE-2026-47102 is a privilege escalation vulnerability in LiteLLM's /user/update endpoint, which does not restrict field updates, allowing users to self-promote to proxy_admin…
CVE-2026-42271 — BerriAI LiteLLM Command Injection Vulnerability
BerriAI LiteLLM Command Injection Vulnerability Apply mitigations per vendor instructions, follow applicable BOD 22-01 guidance for cloud services, or discontinue use of…