LIVE · cybersecurity feed
Live wire
CVE-2024-3848 · LFProjects MLflow Path Traversal Vulnerability Added To VulnCheck KEVCVE-2026-118267 · WPDataAccess Incorrect Authorization Flaw Exploited Same Day As DisclosureCVE-2026-118066 · LatePoint Improper Authentication Vulnerability Exploited On Day Of DisclosureCVE-2026-132224 · Optimizely Web Experimentation Flaw Exploited Same Day as DisclosureCVE-2026-133968 · Project-MONIA MONAI Label Path Traversal Exploited On Disclosure DateCairn AI Framework Used in Autonomous Zero-Day ExploitationAmazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-DayCVE-2026-129975 · GnuPG Warns Critical GPGME Flaw Could Expose App Data via Malicious OpenPGP KeysCVE-2026-129448 · Hackers Exploit Critical VMware, Cisco, and Apache Flaws as Espionage Attacks EmergeCTO of ‘RansomwareHelp’ Indicted for Wire Fraud
ai

AI Agent Gateway: Open-source tool keeps credentials out of agent configs

Tuskira has released AI Agent Gateway, an open-source tool designed to enhance the security of AI agent deployments by centralizing credential management and access control. The gateway operates as an intermediary between AI agents and the services they interact with, including both tool servers (referred to as MCP tools) for platforms like GitHub and Jira, and various large language model…

ZeroDay News ·

Source: Help Net Security

Tuskira has released AI Agent Gateway, an open-source tool designed to enhance the security of AI agent deployments by centralizing credential management and access control. The gateway operates as an intermediary between AI agents and the services they interact with, including both tool servers (referred to as MCP tools) for platforms like GitHub and Jira, and various large language model (LLM) providers.

Traditionally, AI agents often store model keys and MCP credentials directly within their configuration files, distributed across developer laptops and continuous integration (CI) runners. This practice creates multiple points of exposure, as compromise of any single configuration file can lead to the theft of sensitive credentials. Furthermore, without a centralized control mechanism, there is no inherent check on an agent's permissions when it attempts to use a tool.

The AI Agent Gateway addresses these vulnerabilities by ensuring that agents never directly possess sensitive credentials. Instead, an agent registers the gateway as its MCP server and includes a gateway key and a profile name with each request. Upon receiving a request, the gateway first authenticates the gateway key, which is linked to a specific tenant and role. It then verifies whether the designated profile is authorized to use the requested tool. If the request is denied, an error is logged, and the call is blocked from reaching the backend. If approved, the gateway retrieves the actual credential from an encrypted store and attaches it to the outgoing request, effectively abstracting the credential from the agent.

This access control is enforced in real-time at the moment of the call, augmenting the gateway's ability to prune the list of tools an agent is even aware of. Consequently, even if an agent is manipulated into attempting to call a tool it was never shown, the gateway will still refuse the request.

The gateway also supports routing LLM traffic, allowing organizations to manage access to providers such as Anthropic (directly or via AWS Bedrock), OpenAI, and Gemini. By adjusting an SDK's base URL, model traffic can be directed through the gateway, which then records token usage and estimates costs for each call.

Tuskira highlights two default configurations that require careful attention. First, profiles are only bound to keys when explicitly configured. An unbound key allows the caller to specify any profile in a request header, meaning a leaked unbound key could grant access to any profile's permissions. Tuskira recommends binding each key to its specific profile to limit the scope of a leaked key, such as a CI key, to only what its associated profile permits. The sample CI profile provided by Tuskira allows access to only one tool.

Second, the demo stack of the gateway stores LLM request and response bodies, capped at 1 MiB each, for display in the console. These bodies can contain sensitive prompts and code sent by agents. Tuskira advises users to disable this storage setting if privacy is a concern.

The shipped Docker Compose file for the gateway permits outbound connections to the host machine and the loopback range for local testing. Tuskira instructs users to remove these exceptions in any shared or production environment. By default, the gateway otherwise blocks connections to private and loopback addresses and consistently blocks the cloud metadata address.

The AI Agent Gateway is available for free on GitHub and runs on macOS and Linux, with Windows support through WSL2 being untested. The repository includes practical examples for integration with various tools and platforms, including Claude Code, Cursor, VS Code, Codex CLI, Python agents, and Kubernetes.

ai
ShareXLinkedInWhatsAppFacebook

More News

view all →
patch

Weekly Update 531: Optimizely. Script Dependencies & Third Parties

A recent disclosure notice regarding Optimizely has highlighted ongoing concerns surrounding the security of third-party script dependencies. The incident underscores a growing trend where organizations point to external vendors when explaining security lapses, a practice that critics argue serves to deflect institutional accountability rather than addressing the underlying technical risks.

nation-state

FBI Investigating Apparent Hack of Its Key National Criminal Justice Database, AP Source Says

The Federal Bureau of Investigation is currently conducting an investigation into a potential security breach involving the National Crime Information Center, a critical repository of criminal justice data. The database, which is managed by the FBI, serves as a centralized resource for federal, state, and local law enforcement agencies. It contains sensitive information including records on…

breach

Rackspace Spot breach let hackers access customer Kubernetes secrets

Rackspace has confirmed a security breach affecting its Rackspace Spot cloud platform, a service designed for managing containerized applications through Kubernetes. The unauthorized access occurred on November 17, 2026, spanning a window from approximately 00:20 to 22:00 UTC. The company discovered the intrusion on November 18 following a report from a customer and subsequently verified that…

CVE-2024-3848high

LFProjects MLflow Path Traversal Vulnerability Added To VulnCheck KEV

The LFProjects MLflow path traversal vulnerability, CVE-2024-3848, has been added to the VulnCheck KEV catalogue, 894 days after its initial publication.

CVE-2026-118267high

WPDataAccess Incorrect Authorization Flaw Exploited Same Day As Disclosure

The wp_data_access plugin for WordPress faces active exploitation following a zero-day disclosure, yet it remains absent from major federal vulnerability catalogues.

CVE-2026-118066high

LatePoint Improper Authentication Vulnerability Exploited On Day Of Disclosure

The LatePoint plugin for WordPress is currently under exploitation, with the vulnerability appearing in the VulnCheck KEV catalogue on the same day it was published.