Unauthenticated MCP tool invocation via empty secret
Published Jun 17, 2026 · Updated Jun 17, 2026
Missing authentication in Network-AI 5.7.1 and earlier allows remote attackers to invoke privileged MCP tools over the SSE endpoint. McpSseServer._isAuthorized() returns true when its configured secret is empty, so requests without an Authorization header reach handleRPC and dispatch tools. Exploitation requires a non-browser path to the port, such as SSRF or a non-loopback bind, and permits reading or changing orchestrator configuration, spawning agents, and managing tokens.
Summary
What happened
Missing authentication in Network-AI 5.7.1 and earlier allows remote attackers to invoke privileged MCP tools over the SSE endpoint. McpSseServer._isAuthorized() returns true when its configured secret is empty, so requests without an Authorization header reach handleRPC and dispatch tools. Exploitation requires a non-browser path to the port, such as SSRF or a non-loopback bind, and permits reading or changing orchestrator configuration, spawning agents, and managing tokens.
The record
- CVE
- CVE-2026-48814
- Published
- Jun 17, 2026
- Updated
- Jun 17, 2026
- Vendor
- Jovancoding
- Product
- Network-AI
- Classifications
- CWE-306, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 17, 2026CVE publishedPublication date reported by the CVE source.
- Jun 17, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 5.7.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- poc/legend-networkai-empty-secret.tsproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo