LOWAi
Global

CVE-2026-115419 - Unintended disclosure of data element to wrong session in Strands Agents SDK A2A Server

·Source: AWS Security Bulletins

Updated:

Executive Summary

Bulletin ID: 2026-146-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 10/22/2026 13:00 PM PDT Description: Strands Agents is an open-source SDK, available for Python and TypeScript, for building AI agents. The SDK includes an Agent2Agent (A2A) server component that exposes an agent over HTTP so other agen

Analysis

Bulletin ID: 2026-146-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 10/22/2026 13:00 PM PDT Description: Strands Agents is an open-source SDK, available for Python and TypeScript, for building AI agents. The SDK includes an Agent2Agent (A2A) server component that exposes an agent over HTTP so other agents and clients can call it. We identified CVE-2026-115419, an issue where the A2A server did not properly isolate conversation state between callers. An authenticated remote user could access another caller's conversation history or influence model behavior for other callers in multi-tenant deployments. Impacted versions: - strands-agents (Python): all versions containing the multiagent.a2a module, - @strands-agents/sdk (TypeScript): Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin. Read this article

Indicators of Compromise (3)

CVE (1)
CVE-2026-115419
NVDMITRE CVE
URL (1)
https://aws.amazon.com/security/security-bulletins/2026-146-aws/
VirusTotalURLhaus
Domain (1)
aws.amazon.com
VirusTotalURLhaus
Source Attribution

Originally published by AWS Security Bulletins on Oct 22, 2026.

Related Threats

MEDIUMAi

Independent Auditors Find Gaps in OpenAI Agent Monitoring

<img src="https://ismg-cdn.nyc3.cdn.digitaloceanspaces.com/articles/independent-auditors-find-gaps-in-openai-agent-monitoring-image_small-1-a-33183.jpg" align=right hspace=4><b>METR and Redwood Uncover Codex Safeguard Bypasses, OpenAI Says Flaws Now Patched</b><br>Third-party artificial intelligence safety evaluators found several vulnerabilities in OpenAI's monitoring system for its coding agents

Bank Info Security
CRITICALAi

GitLab critical patches include one for a bug that allows code execution by unauthenticated users

GitLab on Wednesday published updated versions of its Community Edition (CE) and Enterprise Edition (EE) that address a dozen bugs and security issues, including some that allow various unauthenticated actions. The most serious of the security issues, labeled critical in severity, is CVE-2026-110264 , an integer overflow issue. “GitLab has remediated an issue that, under certain conditions, could

CVE-2026-110264CVE-2026-15723
CSO Online
CRITICALAi

ThreatsDay: AI Secrets Leak, PingCAP Source Theft, Signal Hang-Up Flaw, Laravel Auth Bypass + 21 More

This week has already been rough for cybersecurity. Critical PHP and GitLab RCE flaws, serious Linux security bugs, compromised eMudhra certificates, a Node.js RCE flaw, a hacked LiteLLM release, and hundreds of hijacked Tor relays. That's a lot to deal with in just a few days. And the week isn't even over yet. But those big headlines are only half the story. Stolen passwords, exposed

The Hacker News