EUVD-2026-54950
GHSA-6fh8-4v8j-r4gw
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Network-reachable SSRF gated by low-privilege auth (PR:L); no scope change; low-impact triad consistent with limited SSRF read/pivot capability.
Primary rating from Vendor (vuldb).
CVSS VectorVendor: vuldb
Lifecycle Timeline
1DescriptionCVE.org
A vulnerability has been found in NocteDefensor LudusMCP 1.0.24. Affected by this vulnerability is an unknown functionality of the file src/tools/rangeConfig.ts of the component read_range_config. The manipulation of the argument Source leads to server-side request forgery. The attack may be initiated remotely. The project was informed of the problem early through an issue report but has not responded yet.
AnalysisAI
Server-side request forgery in NocteDefensor LudusMCP 1.0.24 allows a low-privileged remote attacker to manipulate the Source argument of the read_range_config component in src/tools/rangeConfig.ts, causing the server to issue arbitrary outbound HTTP requests. The CVSS 4.0 vector (E:P) confirms proof-of-concept exploit code exists, though no active exploitation has been observed and no CVE entry appears in the CISA KEV catalog. Impact across confidentiality, integrity, and availability is rated low, and no scope change to subsequent systems is indicated - making this a low-severity but non-trivial SSRF affecting a niche Model Context Protocol server.
Technical ContextAI
LudusMCP is an MCP (Model Context Protocol) server tool - a class of software providing structured tool interfaces to AI agents. The vulnerable component, read_range_config, is implemented in TypeScript at src/tools/rangeConfig.ts and accepts a Source parameter that is passed unsanitized into an outbound request handler, satisfying CWE-918 (Server-Side Request Forgery). The root cause is insufficient validation of the Source argument before it is used to construct or initiate a server-side HTTP/network request, allowing an attacker to redirect the server's request to arbitrary internal or external destinations. No CPE string was provided in the input data; the affected product is NocteDefensor LudusMCP version 1.0.24, hosted at github.com/NocteDefensor/LudusMCP. The MCP protocol context means this tool is likely invoked by an AI agent runtime, so the attack surface is constrained to callers with valid MCP session credentials.
RemediationAI
No vendor-released patch has been identified at time of analysis; the project maintainer has not responded to the disclosure per the CVE description. As a primary compensating control, operators should restrict access to the LudusMCP server to trusted, authenticated AI agent runtimes only and enforce network egress filtering on the host running LudusMCP to block unexpected outbound connections to internal RFC-1918 address ranges and cloud metadata endpoints (e.g., 169.254.169.254). Additionally, reviewing and hardening the read_range_config tool to validate or allowlist acceptable Source values before any network request is initiated would mitigate the root cause at the application level. Monitoring outbound connections from the MCP server process for anomalous destinations is a useful detective control. Track the upstream repository at https://github.com/NocteDefensor/LudusMCP/ and the VulDB entry at https://vuldb.com/vuln/387234 for patch availability updates.
Same weakness CWE-918 – Server-Side Request Forgery (SSRF)
View allShare
External POC / Exploit Code
Leaving vuln.today