CVE-2026-18830 Insufficient input validation in Amazon Bedrock AgentCore harness InvokeHarness API

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

CVE-2026-18830 Insufficient input validation in Amazon Bedrock AgentCore harness InvokeHarness API

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required...

CVE-2026-18830

The CVE-2026-18830 issue affects the Amazon Bedrock AgentCore harness, specifically the InvokeHarness API. It arises from insufficient input validation in, or surrounding, the harness, which could allow an authenticated remote user to execute configured tools by sending crafted content blocks in ...

Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems

Autonomous multi-agent systems AMAS built on large language models LLMs, such as Hermes, increasingly rely on inference-time harnesses to coordinate reasoning and action. Constructing these harnesses requires substantial engineering effort and computational resources, as they are iteratively...

Microsoft Says New Cybersecurity AI Model Helps MDASH Score 95.95% at Half the Cost

Microsoft has launched its first cybersecurity-specific model inside MDASH , its multi-model vulnerability identification and remediation harness. The company says MDASH, using MAI-Cyber-1-Flash and GPT-5.4, scored 95.95% on CyberGym. It also claims the configuration costs 50% less than its curre...

Incorrect Authorization

Overview @ai-sdk/harness-opencode is a The OpenCode harness connects HarnessAgent to OpenCode through a sandboxed bridge. Affected versions of this package are vulnerable to Incorrect Authorization through the tool relay in tool-relay-auth.ts and tool-relay.ts. An attacker can invoke host-exposed...

Incorrect Authorization

Overview @ai-sdk/harness-codex is a HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex CLI. The adapter ships a bridge process that runs inside a sandbox and talks to the host over a WebSocket on a sandbox-proxied l Affected versions of this package are vulnerable to Incorrect...

CVE-2026-64650

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64651

The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path host-tool-mcp.mjs. This allows untrusted code executing in the...

EUVD-2026-46102

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650

The CVE concerns the @ai-sdk/harness-opencode tool (HarnessV1 adapter backed by @openai/codex-sdk) that drives the codex CLI. Prior to version 1.0.29, it relayed requests from any process whose command line contained an allowed helper script path (Codex CLI shim), allowing untrusted sandbox code ...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64650 AI SDK Codex Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool is an HarnessV1 adapter backed by @openai/codex-sdk, which drives the codex command line interface. Prior to version 1.0.29, the tool relay authorizes requests from any process whose command line contains an allowed helper script path the Codex CLI shim. This...

CVE-2026-64651 AI SDK OpenCode Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path host-tool-mcp.mjs. This allows untrusted code executing in the...

EUVD-2026-46098

The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path host-tool-mcp.mjs. This allows untrusted code executing in the...

CVE-2026-64651 AI SDK OpenCode Harness Tool Relay Authorization Bypass

The @ai-sdk/harness-opencode tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path host-tool-mcp.mjs. This allows untrusted code executing in the...

CVE-2026-64651

The CVE-2026-64651 entry concerns the @ai-sdk/harness-opencode tool that connects HarnessAgent to OpenCode via a sandboxed bridge. Before version 1.0.28, the tool would relay requests from any process whose command line included an allowed helper script path (host-tool-mcp.mjs), enabling untruste...

PT-2026-61723

Name of the Vulnerable Software and Affected Versions @ai-sdk/harness-opencode versions prior to 1.0.28 Description The tool connects HarnessAgent to OpenCode via a sandboxed bridge. The tool relay authorizes requests from any process whose command line contains the allowed helper script path...