MikeTrendsTrends right now
AI: reposAPI

search

AI Agent Gateway

Trends

  1. 1
    Open-source AI Agent Gateway keeps credentials out of agent configs▼AI Agent Gateway: Open-source tool keeps credentials out of agent configs✉newsTechnologySoftware1 d ago

    A new open-source tool called AI Agent Gateway has been released, designed to keep credentials out of AI agent configurations. Instead of embedding API keys and secrets directly in agent setup files, the gateway manages authentication separately, reducing the risk of credential leaks. It targets developers building AI agents, a growing area where insecure handling of secrets is a common concern.

  2. 2
    Critical CVE in GitLab's AI Gateway Sparks Security Review●Earlier this month, a critical vulnerability showed up in GitLab's AI Gateway — CVE-2026-90970, CVSS... # ai # securityMmastodonTechnologySoftware33 d ago

    A critical vulnerability, CVE-2026-90970, was discovered earlier this month in GitLab's AI Gateway, drawing attention to how AI agent permissions are handled in developer tools. The flaw, rated with a high CVSS severity score, has prompted security-minded developers to re-examine their own systems and question whether permission models for AI agents are properly isolated from core infrastructure.

  3. 3
    Cloudflare adds Web Search to AI Gateway for agent grounding●Cloudflare has added a native Web Search API to its AI Gateway, built in partnership with search... # ai # automation #MmastodonBusiness36 d ago

    Cloudflare has launched a native Web Search API within its AI Gateway, built in partnership with a search provider, allowing AI agents to ground their responses in live web results. The feature is aimed at developers building automation and agentic applications, letting models pull fresh information instead of relying solely on static training data. Developers are discussing the move as part of the broader push to make AI tools more reliable and up to date.

  4. 4
    GitLab warns of critical RCE flaw in AI Gateway▼⚠️ CRITICAL: GitLab warns of critical RCE vulnerability in AI Gateway service GitLab disclosed CVE-2026-90970, a criticaMmastodonTechnologyCybersecurity25 d ago

    GitLab has disclosed CVE-2026-90970, a critical remote code execution vulnerability in its AI Gateway service. The flaw allows authenticated users with Duo Agent Platform access to escape the prompt sandbox and execute arbitrary commands. Self-hosted instances are affected, and security teams are being urged to patch promptly.

  5. 5
    GitLab patches critical AI Gateway flaw allowing command execution●🤖 GitLab patches CVE-2026-90970 (CVSS 9.9, critical) in the AI Gateway: a logged-in user with Duo Agent Platform accessMmastodonTechnologyCybersecurity16 d ago

    GitLab has released fixes for CVE-2026-90970, a critical vulnerability (CVSS 9.9) in its AI Gateway. An authenticated user with access to the Duo Agent Platform can run commands on the gateway. Only self-hosted gateway deployments are affected. Patches are available in versions 19.2.4, 19.3.2 and 19.4.1, and administrators are urged to update immediately.

Repos