CoreBreak Vulnerability Exposes AI Agent Frameworks to Unauthorized Tool Use

Techtimes

CoreBreak Vulnerability Exposes AI Agent Frameworks to Unauthorized Tool Use

First seen 7 Aug 2026, 08:28 UTC • •70.5

Article Content

1 / 10

Browse articles

ThreatCluster •August 8, 2026 at 08:07 UTC

•CoreBreak vulnerability allows unauthorized tool invocation in AI agent frameworks.
•AWS's InvokeHarness API was assigned CVE-2026-18830 and patched on July 31, 2026.
•Strands Python SDK remains unpatched, leaving a potential attack vector open.

Security researchers revealed multiple vulnerabilities in AI agent frameworks, allowing unauthorized tool use and potential remote code execution (RCE). The CoreBreak vulnerability affects Amazon Web Services (AWS), Google, and Vercel, with AWS's InvokeHarness API being a primary target. AWS assigned CVE-2026-18830 to a flaw enabling attackers to bypass model authorization and invoke tools directly. While AWS and Google have patched their respective vulnerabilities, the Strands Python SDK remains unpatched. The flaws were disclosed during Black Hat USA 2026, highlighting risks in agent orchestration and tool execution logic. The vulnerabilities could lead to significant security breaches if exploited. The overall impact spans multiple frameworks, including LangChain and Microsoft Agent Framework, with various attack vectors identified.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Answers cite the sources they use

Updated 45d ago How this analysis works

Timeline

2026-07-16

Google patches vulnerabilities in ADK

Google released fixes for the ADK, addressing issues including a continuation-forgery vulnerability.

2026-07-20

CVE-2026-64650 and CVE-2026-64651 published

Two vulnerabilities were disclosed affecting various AI frameworks, including LangChain.

2026-07-29

CVE-2026-18236 published

Google published a CVE for a vulnerability in the ADK that allowed insecure deserialization.

2026-08-04

CVE-2026-18830 published

AWS assigned CVE-2026-18830 for a vulnerability in the InvokeHarness API that allowed unauthorized tool invocation.

2026-08-06

CoreBreak vulnerability disclosed at Black Hat USA 2026

Researchers presented findings on the CoreBreak vulnerability affecting multiple AI frameworks, including AWS and Google.

More articles in this cluster (9)

Following this threat?

Track Amazon Web Services and CVE-2026-18236 in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Continue Reading

Critical WSO2 API Manager Vulnerability Under Active Exploitation A critical vulnerability (CVE-2026-5430) in WSO2 API Manager is being actively exploited, allowing unauthenticated attackers to forge admin tokens via JWT authentication bypass. This flaw, which has a CVSS score of 10.0, affects multiple WSO2 products including API Manager, Universal Gateway, Traffic Manager, and API…

Critical Linux Kernel Vulnerability CVE-2025-39682 Under Active Exploitation A critical vulnerability (CVE-2025-39682) in the Linux kernel allows remote code execution through mishandling of zero-length TLS records. This flaw affects kTLS-enabled hosts running vulnerable kernel versions, exposing them to attackers without authentication. CISA added this vulnerability to its Known Exploited…