Lucene search
+L

34 matches found

Positive Technologies
Positive Technologies
added 2026/07/20 12:0 a.m.22 views

PT-2026-61582

Network-AI npm: network-ai versions 5.12.2 through 5.13.3 fail to apply the configured authorization check checkAuth/secret to the ApprovalInbox GET read routes, so even when an operator configures a secret, unauthenticated actors can access sensitive approval request details. The GET...

9.3CVSS5.3AI score0.00408EPSS
SaveExploits0References3
OSV
OSV
added 2026/06/19 9:42 p.m.10 views

GHSA-MXJX-28VX-XJJJ Network-AI: ApprovalInbox HTTP server has no authentication — anyone can approve pending agent actions

Summary network-ai's ApprovalInbox lib/approval-inbox.ts is a shipped, exported, documented feature — "a web-accessible approval queue with REST API … and SSE streaming" SECURITY.md. It is the network surface of the human-in-the-loop Approval Gate, which ApprovalGate uses to require explicit huma...

5.9CVSS6.1AI score0.00132EPSS
SaveExploits0References4
OSV
OSV
added 2026/06/19 9:42 p.m.14 views

GHSA-JVCM-F35G-W78P Network-AI: AgentRuntime sandbox path-prefix checks allow file access outside the configured base directory

Summary AgentRuntime promises scoped file access under a configured sandbox basePath, but its path containment checks use raw string prefix tests. A sandbox base such as /tmp/network-ai-sandbox also matches a sibling path such as /tmp/network-ai-sandboxevil/secret.txt. An agent/user that can call...

6.5CVSS5.9AI score0.00131EPSS
SaveExploits0References4
OSV
OSV
added 2026/06/19 1:35 p.m.11 views

GHSA-QW6V-5FCF-5666 Network-AI: Improper Neutralization of Special Elements used in an OS Command

Summary The agent sandbox gates shell commands behind an allowlist SandboxPolicy.isCommandAllowed, which THREATMODEL.md calls the main control against a compromised agent Adversary 3.2. The allowlist glob-matches the whole command string, but ShellExecutor runs that string through /bin/sh -c. So...

9.9CVSS6.5AI score0.0037EPSS
SaveExploits0References2
OSV
OSV
added 2026/06/19 1:34 p.m.13 views

GHSA-R78R-RWRF-RJWP Network-AI: CVE-2026-46701 fix incomplete — empty default secret still authorizes all requests

Advisory / Disclosure Network-AI — CVE-2026-46701 fix is incomplete: the "Empty Default Secret" unauth path survives Target: Jovancoding/Network-AI npm network-ai, latest v5.7.1 Status: the advisory "Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret" named three flaws. The...

9.1CVSS5.9AI score0.00297EPSS
SaveExploits0References5
RedhatCVE
RedhatCVE
added 2026/06/05 7:16 p.m.12 views

CVE-2026-42856

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to 5.1.3, the MCP HTTP transport accepts JSON-RPC tools/call requests with no authentication, session, origin, or token check, and dispatches them directly to the orchestrator's tool registry. The default bind address is 0.0.0.0. ...

8.7CVSS5.5AI score0.00471EPSS
SaveExploits0References1
Patchstack
Patchstack
added 2026/05/21 10:39 p.m.11 views

NPM: Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

NPM: Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret vulnerability discovered by ? in WordPress Npm network-ai versions = 5.4.4...

5.8AI score0.00168EPSS
SaveExploits0References2Affected Software1
Positive Technologies
Positive Technologies
added 2026/05/21 12:0 a.m.27 views

PT-2026-42703

Name of the Vulnerable Software and Affected Versions Network-AI versions prior to 5.4.5 Description The MCP SSE server defaults to an empty secret via the NETWORK AI MCP SECRET environment variable, which causes the isAuthorized function to return true for all requests regardless of whether an...

7.6CVSS5.3AI score0.00168EPSS
SaveExploits0References10
Circl
Circl
added 2026/05/16 3:11 p.m.24 views

CVE-2026-46701

creationtimestamp| type| source ---|---|--- 2026-05-16 15:11:55+00:00| published-proof-of-concept| https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-j3vx-cx2r-pvg8 2026-06-17 22:38:26+00:00| seen| https://bsky.app/profile/cve.skyfleet.blue/post/3mojevvheah2c 2026-06-19...

7.6CVSS5.8AI score0.00168EPSS
SaveExploits0References3
NVD
NVD
added 2026/05/11 6:16 p.m.57 views

CVE-2026-42856

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to 5.1.3, the MCP HTTP transport accepts JSON-RPC tools/call requests with no authentication, session, origin, or token check, and dispatches them directly to the orchestrator's tool registry. The default bind address is 0.0.0.0. ...

8.7CVSS0.00471EPSS
SaveExploits0References1
Cvelist
Cvelist
added 2026/05/11 5:42 p.m.79 views

CVE-2026-42856 Network-AI: Missing authentication on MCP HTTP endpoint allows unauthenticated privileged tool calls

Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to 5.1.3, the MCP HTTP transport accepts JSON-RPC tools/call requests with no authentication, session, origin, or token check, and dispatches them directly to the orchestrator's tool registry. The default bind address is 0.0.0.0. ...

8.7CVSS0.00471EPSS
SaveExploits0References1
CNNVD
CNNVD
added 2026/05/11 12:0 a.m.13 views

Network-AI 访问控制错误漏洞

Network-AI is a multi-agent orchestration and governance tool developed by Jovan Marinovic. Versions prior to Network-AI 5.1.3 contained an access control vulnerability. This vulnerability stemmed from the lack of authentication, session, source, or token checks for JSON-RPC tool calls transmitte...

8.7CVSS5.8AI score0.00471EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
added 2026/05/05 12:0 a.m.31 views

PT-2026-37283

Name of the Vulnerable Software and Affected Versions Network-AI versions prior to 5.1.3 Description The MCP HTTP transport accepts JSON-RPC tools/call requests without requiring authentication, sessions, origins, or token checks, dispatching them directly to the orchestrator's tool registry...

8.7CVSS5.8AI score0.00471EPSS
SaveExploits0References8
Circl
Circl
added 2026/04/24 2:5 p.m.15 views

CVE-2026-42856

creationtimestamp| type| source ---|---|--- 2026-04-24 14:05:57+00:00| published-proof-of-concept| https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-fj4g-2p96-q6m3...

8.7CVSS5.8AI score0.00471EPSS
SaveExploits0References1
Rows per page
Query Builder