CVE-2026-19329: andreahaku codex_mcp · Injection
Source GCVE Database
Public exploit available · CVSS 4.8 Medium.
Data as of 7 Nov 2026, 23:24 UTC
- EPSS
- 0.7% chance of exploitation in 30 days – higher than 56% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:PExploitation evidence
Disclosed: evidence found.
CVE published 9 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
CVSS exploit maturity: proof of concept public
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 8 Nov 2026.
What to do
Affected software
| Product | Affected | Fixed in |
|---|---|---|
| andreahakucodex_mcp | Affected
| Fixed in– |
AI-suggested
Users should restrict local access to trusted users only and monitor for any updates from the project.
Description
A command injection vulnerability exists in the andreahaku codex_mcp project in an unknown function within src/codex-process-simple.ts. The vulnerability arises from improper handling of the argument 'model' and requires local access to exploit. The project does not use versioning, so affected versions cannot be precisely identified. No patch or vendor response has been provided yet.
References
- nvd.nist.gov/vuln/detail/CVE-2026-19329 (opens in a new tab)
- github.com/andreahaku/codex_mcp/issues/1 (opens in a new tab)
- github.com/andreahaku/codex_mcp (opens in a new tab)
- vuldb.com/cve/CVE-2026-19329 (opens in a new tab)
- vuldb.com/submit/865246 (opens in a new tab)
- vuldb.com/vuln/387163 (opens in a new tab)
- vuldb.com/vuln/387163/cti (opens in a new tab)