PT-2026-82552

GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.10 to 19.0.12, 19.1 to 19.1.7, and 19.2 to 19.2.2 that could have allowed an authenticated user with Duo Agent Platform access to redirect outbound model requests to an...

MLflow AI Gateway permits SSRF through an unvalidated api_base

MLflow's AI Gateway accepts an authconfig.apibase value when creating a gateway secret mlflow/server/handlers.py, creategatewaysecret with no validation of scheme, host, or IP range; the value is stored verbatim. The gateway proxy endpoint mlflow/server/gatewayapi.py, rawproxy subsequently issues...

PT-2026-83239

Name of the Vulnerable Software and Affected Versions Bifrost versions prior to 1.5.17 Description Bifrost is an enterprise AI gateway for routing requests to model providers. A Server-Side Request Forgery SSRF issue exists because the isPublicIP function in core/providers/utils/fetch.go...

EUVD-2026-43249

A flaw has been found in Helicone ai-gateway up to 0.2.0-beta.30. This affects the function buildtargeturl of the file ai-gateway/src/dispatcher/service.rs of the component AWS Metadata Service. Executing a manipulation of the argument extractedpathandquery can lead to server-side request forgery...

CVE-2026-15508

A flaw has been found in Helicone ai-gateway up to 0.2.0-beta.30. This affects the function buildtargeturl of the file ai-gateway/src/dispatcher/service.rs of the component AWS Metadata Service. Executing a manipulation of the argument extractedpathandquery can lead to server-side request forgery...

CVE-2026-15508 Helicone ai-gateway AWS Metadata Service service.rs build_target_url server-side request forgery

A flaw has been found in Helicone ai-gateway up to 0.2.0-beta.30. This affects the function buildtargeturl of the file ai-gateway/src/dispatcher/service.rs of the component AWS Metadata Service. Executing a manipulation of the argument extractedpathandquery can lead to server-side request forgery...

CVE-2026-15508

Helicone ai-gateway (up to 0.2.0-beta.30) is affected. The flaw is in the AWS Metadata Service component, specifically the build_target_url function in ai-gateway/src/dispatcher/service.rs, where manipulating extracted_path_and_query can trigger server-side request forgery. Exploitation is possib...

PT-2026-57575

A flaw has been found in Helicone ai-gateway up to 0.2.0-beta.30. This affects the function build target url of the file ai-gateway/src/dispatcher/service.rs of the component AWS Metadata Service. Executing a manipulation of the argument extracted path and query can lead to server-side request...

AI Gateway Connected to Amazon Bedrock Hijacked for Cryptomining

Darktrace says a LiteLLM AI gateway linked to Amazon Bedrock was compromised for cryptomining after signs of exposed SSH activity...

GO-2026-5121 Envoy AI Proxy - MCP Message Smuggling Vulnerability in github.com/envoyproxy/ai-gateway

Envoy AI Proxy - MCP Message Smuggling Vulnerability in github.com/envoyproxy/ai-gateway...

GHSA-G35P-PX32-WHV6 MLflow: Environment variable injection in AI Gateway secrets enables server-side credential exfiltration

A vulnerability in mlflow/mlflow versions prior to 3.11.0 allows for the resolution of environment variables in AI Gateway secrets, which can be exploited to exfiltrate sensitive server-side environment credentials to an attacker-controlled endpoint. This issue arises because the apikey field in...

MLflow: Environment variable injection in AI Gateway secrets enables server-side credential exfiltration

A vulnerability in mlflow/mlflow versions prior to 3.11.0 allows for the resolution of environment variables in AI Gateway secrets, which can be exploited to exfiltrate sensitive server-side environment credentials to an attacker-controlled endpoint. This issue arises because the apikey field in...

CVE-2026-4035

A vulnerability in mlflow/mlflow versions prior to 3.11.0 allows for the resolution of environment variables in AI Gateway secrets, which can be exploited to exfiltrate sensitive server-side environment credentials to an attacker-controlled endpoint. This issue arises because the apikey field in...

PYSEC-2026-2222

A vulnerability in mlflow/mlflow versions prior to 3.11.0 allows for the resolution of environment variables in AI Gateway secrets, which can be exploited to exfiltrate sensitive server-side environment credentials to an attacker-controlled endpoint. This issue arises because the apikey field in...

EUVD-2026-34068

A vulnerability in mlflow/mlflow versions prior to 3.11.0 allows for the resolution of environment variables in AI Gateway secrets, which can be exploited to exfiltrate sensitive server-side environment credentials to an attacker-controlled endpoint. This issue arises because the apikey field in...

MLflow 安全漏洞

MLflow is an open-source platform that simplifies machine learning development. It includes features for tracking experiments, packaging code for reproducible runs, and sharing and deploying models. Versions of MLflow prior to 3.11.0 contained a security vulnerability, which was caused by an issu...

GHSA-4GPH-2HHR-5MWG Envoy AI Proxy - MCP Message Smuggling Vulnerability

Envoy AI Gateway was found to be affected by a protocol parser differential vulnerability due to improper implementation of the JSON-RPC 2.0 specification. Such differential causes a MCP message alteration, potentially causing a bypass of security controls in a multi-layered architecture. Accordi...

Envoy AI Proxy - MCP Message Smuggling Vulnerability

Envoy AI Gateway was found to be affected by a protocol parser differential vulnerability due to improper implementation of the JSON-RPC 2.0 specification. Such differential causes a MCP message alteration, potentially causing a bypass of security controls in a multi-layered architecture. Accordi...

AI Gateway secret API accepts `$ENV_VAR` references and can be remotely abused to exfiltrate server-side environment credentials to an attacker-controlled upstream endpoint. And the leaked credentials can be further leveraged to break security boundaries.

Analyzed project versions: Current target branch: master Current HEAD: dc8ef3cbbefccf7384f4e3023492aae635c5d5d0 Fix 403 Forbidden for artifact list via query param when defaultpermission=NOPERMISSIONS 21220, commit date: 2026-03-04 The vulnerability is that AI Gateway secrets allow...

CVE-2026-1868

GitLab has remediated a vulnerability in the Duo Workflow Service component of GitLab AI Gateway affecting all versions of the AI Gateway from 18.1.6, 18.2.6, 18.3.1 to 18.6.1, 18.7.0, and 18.8.0 in which AI Gateway was vulnerable to insecure template expansion of user supplied data via crafted D...