Vulnerability · Published Oct 23, 2026 · Assigned by VulnCheck
CVE-2026-115750mcp-from-openapi from 2.5.0 before 2.9.0 Credential Leak via Cross-Origin Redirects
Low 3.7
In plain English
A low-severity security flaw in mcp-from-openapi from agentfront. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 13% of all known vulnerabilities).
Severity (CVSS 3.1)3.7Low
Exploit odds (30 days)0.2%top 87.3% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official description
mcp-from-openapi from 2.5.0 before 2.9.0 contains a credential exposure vulnerability that allows attackers to capture Authorization and Cookie headers because safeFetch() forwards them on cross-origin redirects. Attackers controlling a spec host or abusing an open redirect can redirect fromURL() spec requests to their own origin to steal bearer tokens or cookies.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| agentfront | mcp-from-openapi | 2.5.0 – before 2.9.0 |
Weakness: CWE-522 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N
References
- GitHub Security Advisory (GHSA-ff5q-5r4v-fw4v) vendor-advisory
- https://github.com/agentfront/mcp-from-openapi/pull/42 issue-tracking, patch
- https://github.com/agentfront/mcp-from-openapi/commit/47fb7a655de33958b0c923490ab244343eb5fc44 patch
- mcp-from-openapi v2.9.0 Release Notes release-notes
- VulnCheck Advisory: mcp-from-openapi from 2.5.0 before 2.9.0 Credential Leak via Cross-Origin Redirects third-party-advisory