CVE-2026-64684 json
RMCP: Custom HTTP headers leak to cross-origin redirect targets
published 2026-09-16 53 d ago modified 2026-09-23 46 d ago also GHSA-9g45-5xwm-f3wc , EUVD-2026-81266
- cvss
- 6.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.5%
- EPSS 0.5% chance of exploitation in 30 days, percentile 43%
- public exploits
- 0
- none known
Summary
RMCP is an official Rust SDK for the Model Context Protocol. Prior to 2.1.0, the rmcp crate's StreamableHttpClientTransport in crates/rmcp/src/transport/common/reqwest/streamable_http_client.rs builds its default_http_client with reqwest's automatic redirect policy and applies caller-supplied values from StreamableHttpClientTransportConfig.custom_headers without marking them as sensitive. When a malicious or compromised MCP endpoint returns a cross-origin 307 or 308 redirect, reqwest follows the redirect and apply_custom_headers causes custom API keys or authentication tokens to be replayed to the new origin, where an attacker can capture and reuse them. The separate auth_header path is not affected because it uses the standard Authorization header, which reqwest strips on cross-origin redirects. This issue is fixed in version 2.1.0.
Patch / fix
- crates.io rmcp 2.1.0
- openai-codex openSUSE Tumbleweed 0.155.1-1.1
opensuse advisories openSUSE-SU-2026:11849-1
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-64684 updated cvss 6.8
rmcp: RMCP: Sensitive HTTP headers leaked during cross-origin redirects
-
Red Hat Enterprise Linux 9 goose, goose 1.38.0-1.el10_2 Red Hat Enterprise Linux 10 goose 1.38.0-1.el10_2affected: workaround, no fix available “Fix deferred”
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- partial
- Assessed
- 51 d ago
Exploit prediction
0.50% chance of exploitation in the next 30 days, higher than 43% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 6.8 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N |
| GitHub | 3.1 | 6.8 | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:C/C:H/I:N/A:N |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| crates.io | rmcp | <2.1.0 |
2.1.0 |
Affected products
- modelcontextprotocol rust-sdk
Classification
- Weakness
-
- CWE-200 Exposure of Sensitive Information to an Unauthorized Actor
References
-
github.com
/modelcontextprotocol/rust-sdk/pull/936
web
-
github.com
/modelcontextprotocol/rust-sdk/commit/496902b9cf2c8a947454718da31829ae776b969b
web
-
github.com
/modelcontextprotocol/rust-sdk/security/advisories/GHSA-9g45-5xwm-f3wc
web
-
github.com
/modelcontextprotocol/rust-sdk/releases/tag/rmcp-v2.1.0
web
-
nvd.nist.gov
/vuln/detail/CVE-2026-64684
advisory
-
github.com
/modelcontextprotocol/rust-sdk
package
Sources
- CVE List CVE-2026-64684
- GitHub Advisory GHSA-9g45-5xwm-f3wc
- NVD CVE-2026-64684
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.