HighVulnerabilityLLM-specific

CVE-2025-61260: OpenAI Codex CLI code execution through malicious MCP configuration files

Source: NVD(opens in a new tab)
Identifier: CVE-2025-61260
Published: April 14, 2026
Record updated: October 9, 2026

Affected: @openai/codex <= 0.23.0
Fixed in: No fixed version was stated when the source was last read.
Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 6.6%

Summary

CVE-2025-61260 affects OpenAI Codex CLI v0.23.0 and earlier. A malicious or compromised repository can trigger code execution when a user runs the codex command inside it, because Codex automatically loads project-local .env and .codex/config.toml files, including malicious MCP (Model Context Protocol) configuration, without user confirmation. Attackers can embed arbitrary commands that execute immediately.

Mitigation

The source does not state a fix yet. Check the original advisory for updates.

Details

Scores and exploitation

EPSS: 6.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on October 15, 2026.
Disclosure date: April 14, 2026

Affected

Packages: @openai/codex@<= 0.23.0
Vendors: OpenAI

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Plugin
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2025-61260

First tracked: April 14, 2026 at 02:07 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 93% (self-assessed)

Topics

Model Context Protocol

Summary

Mitigation

Topics

Related items