EUVD-2026-108507

Strands Agents SDK: Exposure of data element to wrong session in the A2A Server...

GHSA-4V6F-7VJH-6X4M Strands Agents SDK: Exposure of data element to wrong session in the A2A Server

Summary Strands Agents SDK is an open-source SDK, available for Python strands-agents and TypeScript @strands-agents/sdk, for building and running AI agents. An issue exists where, under certain circumstances, the Agent2Agent A2A server shares conversation history across callers with different...

Strands Agents SDK: Exposure of data element to wrong session in the A2A Server

Summary Strands Agents SDK is an open-source SDK, available for Python strands-agents and TypeScript @strands-agents/sdk, for building and running AI agents. An issue exists where, under certain circumstances, the Agent2Agent A2A server shares conversation history across callers with different...

CVE-2026-115419

The A2A server component in Amazon Strands Agents SDK for Python before 1.43.0 and Amazon Strands Agents SDK for TypeScript before 1.5.0 does not properly isolate conversation state between callers. An authenticated remote user could read other tenants' conversation history and add persistent...

CVE-2026-115419

The A2A server component in Amazon Strands Agents SDK for Python before 1.43.0 and Amazon Strands Agents SDK for TypeScript before 1.5.0 does not properly isolate conversation state between callers. An authenticated remote user could read other tenants' conversation history and add persistent...

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

The A2A server component in Amazon Strands Agents SDK for Python before 1.43.0 and Amazon Strands Agents SDK for TypeScript before 1.5.0 does not properly isolate conversation state between callers. An authenticated remote user could read other tenants' conversation history and add persistent...

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

The A2A server component in Amazon Strands Agents SDK for Python before 1.43.0 and Amazon Strands Agents SDK for TypeScript before 1.5.0 does not properly isolate conversation state between callers. An authenticated remote user could read other tenants' conversation history and add persistent...

CVE-2026-115419

The Amazon Strands Agents SDK (Python version before 1.43.0 and TypeScript version before 1.5.0) contains a vulnerability in the A2A server component where conversation state is not properly isolated between callers. This flaw allows an authenticated remote user to access other tenants' conversat...

PT-2026-121658

Name of the Vulnerable Software and Affected Versions Amazon Strands Agents SDK for Python versions prior to 1.43.0 Amazon Strands Agents SDK for TypeScript versions prior to 1.5.0 Description The A2A server component fails to properly isolate conversation state between callers. An authenticated...

amazon-nova-act-mcp (>=1.0.60.0, <=1.20260527102944.0), gherkai-worker-novaact (>=1.4.0, <=1.4.9) +4 more potentially affected by CVE-2026-78379 via strands-agents-tools (>=0.1.9, <=0.2.22)

strands-agents-tools PYPI version =0.1.9, =1.0.60.0, =1.4.0, =2.3.18.0, =0.1.0, =0.1.0, =0.1.0, =0.1.6 Source cves: CVE-2026-78379 Source advisory: SNYK:PYTHON-STRANDSAGENTSTOOLS-19329790...

Improper Neutralization of Input Used for LLM Prompting

Overview strands-agents-tools is an A collection of specialized tools for Strands Agents Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the pythonrepl function in src/strandstools/pythonrepl.py. An attacker can execute arbitrary...

CVE-2026-78379

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

EUVD-2026-65735

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379

Amazon Strands Agents Tools (prior to 0.8.5 ) is affected by an improper input neutralization flaw in its python_repl tool. A remote attacker can craft a prompt that forwards the non_interactive_mode keyword argument through the batch tool, thereby bypassing the human consent gate and achieving a...

amazon-nova-act-mcp (>=1.0.60.0, <=1.20260527102944.0), gherkai-worker-novaact (>=1.4.0, <=1.4.9) +4 more potentially affected by CVE-2026-78379 via strands-agents-tools (>=0.1.9, <=0.2.22)

strands-agents-tools PYPI version =0.1.9, =1.0.60.0, =1.4.0, =2.3.18.0, =0.1.0, =0.1.0, =0.1.0, =0.1.6 Source cves: CVE-2026-78379 Source advisory: MEND:CVE-2026-78379...

CVE-2026-78379: Undefined Security Weakness

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

PT-2026-81489

Name of the Vulnerable Software and Affected Versions Amazon Strands Agents Tools versions prior to 0.8.5 Description Improper neutralization of input used for Large Language Model LLM prompting in the python repl tool allows remote actors to execute arbitrary Python code on the agent's host. Thi...