CVE-2026-92363

CVE-2026-92363 affects the JSON Parser component (file src/stream/sse_parser.cpp) in ag-ui-protocol ag-ui version 1.0 . An unknown function within this component is vulnerable to a remote resource consumption attack requiring low privileges and no user interaction. The CVSS 3.1 base score is 4.3 ...

EUVD-2026-80708

A flaw has been found in ag-ui-protocol ag-ui 1.0. Affected is an unknown function of the file src/stream/sseparser.cpp of the component JSON Parser. Executing a manipulation can lead to resource consumption. The attack may be performed from remote. This patch is called...

CVE-2026-92359

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. The affected element is the function createstrandsapp of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component CORSMiddleware. The manipulation results in permissive cross-domain policy with untrusted...

EUVD-2026-80703

A vulnerability was detected in ag-ui-protocol ag-ui 1.0. This impacts an unknown function of the file crates/ag-ui-client/src/sse.rs of the component SSE Frame Parser. Performing a manipulation results in resource consumption. The attack is possible to be carried out remotely. The pull request t...

CVE-2026-92362

CVE-2026-92362 affects the SSE Frame Parser component in the file crates/ag-ui-client/src/sse.rs of ag-ui-protocol ag-ui 1.0 . The vulnerability allows a remote attacker to trigger resource consumption through manipulation of the parser, potentially leading to a denial-of-service condition. The C...

CVE-2026-92361

A remote resource consumption vulnerability affects the SSE Client component of ag-ui-protocol ag-ui 1.0 , specifically in the file sdks/community/go/pkg/client/sse/client.go. An attacker with low privileges can trigger excessive resource consumption over the network without user interaction, res...

CVE-2026-92360

A medium-severity vulnerability (CVSS 3.1: 6.3 ) exists in ag-ui-protocol ag-ui 1.0 , specifically in the Event Application Layer component. The vulnerable element is the prepareRunAgentInput function in agent/agent.ts , where manipulation of the TEXT_MESSAGE_START argument triggers an origin val...

CVE-2026-92359 ag-ui-protocol ag-ui CORSMiddleware utils.py create_strands_app cross-domain policy

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. The affected element is the function createstrandsapp of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component CORSMiddleware. The manipulation results in permissive cross-domain policy with untrusted...

CVE-2026-92359

CVE-2026-92359 affects ag-ui-protocol ag-ui 0.3.0 , specifically the CORSMiddleware component in the create_strands_app function within integrations/aws-strands/python/src/ag_ui_strands/utils.py. The root cause is a permissive cross-domain policy that allows untrusted domains, potentially enablin...

EUVD-2026-80694

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. The affected element is the function createstrandsapp of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component CORSMiddleware. The manipulation results in permissive cross-domain policy with untrusted...

EUVD-2026-80070

A security flaw has been discovered in ag-ui-protocol ag-ui 0.3.0. Affected is the function urllib.request.urlopen of the file integrations/aws-strands/python/src/aguistrands/utils.py of the component Multimodal Content. The manipulation of the argument Value results in server-side request forger...

CVE-2026-92184

A server-side request forgery (SSRF) vulnerability exists in ag-ui-protocol ag-ui 0.3.0 , affecting the function urllib.request.urlopen in the file integrations/aws-strands/python/src/ag_ui_strands/utils.py within the Multimodal Content component. Manipulation of the argument Value enables the fl...

CVE-2026-65975

CVE-2026-65975 affects Pydantic AI AG-UI Adapter (AG-UI via Agent.to_ag_ui()/AGUIAdapter and Vercel AI via VercelAIAdapter) in Pydantic AI versions 1.88.0–1.107.0 and 2.0.0b1–2.4.x. The bug arises because sanitize_messages uses a stripping index computed before sanitization, so when a trailing cl...

PYSEC-2026-2980 Pydantic AI has Server-Side Request Forgery (SSRF) in URL Download Handling

Summary A Server-Side Request Forgery SSRF vulnerability exists in Pydantic AI's URL download functionality. When applications accept message history from untrusted sources, attackers can include malicious URLs that cause the server to make HTTP requests to internal network resources, potentially...