CVE-2026-115750
3.7 LOWpublic exploit availablePublished 2026-10-23 · Updated 2026-10-23
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD 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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:L/I:N/A:N
Weaknesses
CWE-522
Public exploit & PoC references
- https://github.com/agentfront/mcp-from-openapi/commit/47fb7a655de33958b0c923490ab244343eb5fc44
- https://github.com/agentfront/mcp-from-openapi/pull/42
- https://github.com/agentfront/mcp-from-openapi/releases/tag/v2.9.0
- https://github.com/agentfront/mcp-from-openapi/security/advisories/GHSA-ff5q-5r4v-fw4v
All references
- https://github.com/agentfront/mcp-from-openapi/commit/47fb7a655de33958b0c923490ab244343eb5fc44
- https://github.com/agentfront/mcp-from-openapi/pull/42
- https://github.com/agentfront/mcp-from-openapi/releases/tag/v2.9.0
- https://github.com/agentfront/mcp-from-openapi/security/advisories/GHSA-ff5q-5r4v-fw4v
- https://www.vulncheck.com/advisories/mcp-from-openapi-from-2.5.0-before-2.9.0-credential-leak-via-cross-origin-redirects
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- LOWCVE-2026-100264
- HIGHCVE-2026-100298
- MEDIUMCVE-2026-100569PoC
- UNSCOREDCVE-2026-101034
- LOWCVE-2026-101089PoC
- HIGHCVE-2026-101331
- HIGHCVE-2026-102944PoC
- UNSCOREDCVE-2026-103090PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.