VulnSocial

CVE-2026-45609Disclosure(springaicommunity / mcp_security)

LOWCVSS 6.5 · MEDIUM

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol (MCP) security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to the network. This only affects installations with Dynamic Client Registration (DCR) enabled This vulnerability is fixed in 0.1.9.

springaicommunity CVEsBack to dashboard
0.0/ 10 priority

Sources & remediation

Vendor / third-party advisories
Weakness type (CWE)
CWE-918

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

NONE

Momentum

NONE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

  • mcp_security

Threat summary

  • 1 mentions across 1 observed day

What's happening

  • Technical details provided in 1 signal
  • Disclosure: 1 classified signal
  • 1 total mentions across 1 day

Affected systems

Vendors
springaicommunity
Products
mcp_security

Deep dive

Activity timeline1 mentions / 1d
00111Mentions · 2026-07-12: 1Technical Details · 2026-07-12: 107-12
Signal classification1 categories
Disclosure
1100.0%
Full discourse1 post
  • Atef Ataya@atef_ataya
    Disclosure

    Vulnerability 2 — SSRF via dynamic discovery. CVE-2026-45609. HIGH severity. Spring AI mcp-security framework. Attacker hosts malicious MCP server. Victim client fetches unvalidated URLs from it. Client hits AWS IMDS at 169.254.169.254. IAM credentials walk out the door.

    Post summary

    CVE-2026-45609 is a high‑severity SSRF vulnerability in Spring AI mcp-security framework that allows an attacker to host a malicious MCP server, causing a victim client to reach AWS IMDS and exfiltrate IAM credentials; no exploitation reports, patch, or PoC were provided.

    1000095
    280 followersView on X
CPE platform detail1 entries

1 of 1 entries

PartVendorProductVersionTarget SWTarget HW
Appspringaicommunitymcp_security---

Explore more

Back to dashboardspringaicommunity CVEsmcp_security vulnerabilities