CVE-2026-7817 pgAdmin 4: Local file inclusion and server-side request forgery in LLM API configuration endpoints

Local file inclusion LFI and server-side request forgery SSRF vulnerabilities in pgAdmin 4 LLM API configuration endpoints. User-supplied apikeyfile and apiurl preferences were passed to the LLM provider clients without validation. An authenticated user could read arbitrary server-side files by...

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,...

CVE-2026-41487

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

CVE-2026-41487 Langfuse: Improper role-based-access control in Langfuse LLM connection management allowed users of role “member” to retrieve stored LLM provider API keys

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

CVE-2026-41487

CVE-2026-41487 affects Langfuse (open source LLM engineering platform). From version 3.68.0 up to before 3.167.0, a role-based access control flaw in the LLM connection update flow allowed an authenticated, low-privilege user with the role “member” in a project to request updating an LLM connecti...

CVE-2026-41487 Langfuse: Improper role-based-access control in Langfuse LLM connection management allowed users of role “member” to retrieve stored LLM provider API keys

Langfuse is an open source large language model engineering platform. From version 3.68.0 to before version 3.167.0, there is a role-based-access control flaw in the LLM connection update flow. An authenticated, low-privileged user of role “member” in a project could request the update of an...

CVE-2026-42208

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.81.16 to before version 1.83.7, 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...

CVE-2026-42208

LiteLLM proxy (AI Gateway) versions 1.81.16–1.83.6 suffer a SQL injection in the proxy API key verification path where the caller-supplied key is interpolated into a SQL query during error handling. An unauthenticated attacker can send a crafted Authorization header to LLM routes (e.g., POST /cha...

CVE-2026-42208 LiteLLM: SQL injection in Proxy API key verification

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. From version 1.81.16 to before version 1.83.7, 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...

CVE-2026-42271 LiteLLM: Authenticated command execution via MCP stdio test endpoints

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. 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 /mcp-rest/test/tools/list — accepted a full server configuration i...

LiteLLM SQL注入漏洞

LiteLLM is an open-source application developed by Berri AI. It allows for the use of OpenAI format calls for all LLM APIs. In versions 1.81.16 to 1.83.7 of LiteLLM, there was a SQL injection vulnerability. This vulnerability stemmed from the use of database queries during the check of the proxy...

PT-2026-39011

Name of the Vulnerable Software and Affected Versions Langfuse versions 3.68.0 through 3.166.0 Description A role-based access control flaw exists in the LLM connection update flow. An authenticated user with the "member" role in a project can request an update to an existing LLM connection by...

langfuse 访问控制错误漏洞

Langfuse is an open-source large language model engineering platform developed by Langfuse. Versions 3.68.0 to 3.167.0 contained a access control vulnerability. This vulnerability stemmed from a role-based access control flaw in the LLM connection update process. It could allow low-privilege user...

ClawGuard: Out-Of-Band Detection of LLM Agent Workflow Hijacking Via EM Side Channel

Autonomous LLM agents face a critical security risk known as workflow hijacking, where attackers subtly alter tool and skill invocations. Existing defenses rely on host-internal telemetry such as audit logs, which can be forged if the host OS is compromised. To solve this, we introduce ClawGuard,...

SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems Via Model Context Protocol

The deployment of Large Language Model LLM-generated SQL queries in Artificial Intelligence of Things AIoT systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries that expose sensitive data or execute destructive operations...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42079 PPTAgent: Arbitrary Code Execution via Python eval() of LLM-Generated Code with Builtins in Scope

PPTAgent is an agentic framework for reflective PowerPoint generation. Prior to commit 418491a, PPTAgent is vulnerable to arbitrary code execution via Python eval of LLM-generated code with builtins in scope. This issue has been patched via commit 418491a...

CVE-2026-42076

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...

EUVD-2026-27009

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...

CVE-2026-42076 Evolver: Command Injection via `execSync` in `_extractLLM()` function allows Remote Code Execution

Evolver is a GEP-powered self-evolving engine for AI agents. Prior to version 1.69.3, a command injection vulnerability in the extractLLM function allows attackers to execute arbitrary shell commands on the server. The function constructs a curl command using string concatenation and passes it to...