Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

Is my AI tool safe?Coding agentsOpenAI

Is OpenAI Codex CLI safe?

No tool is safe or unsafe on its own: it depends on what it can reach and how it is set up. The record for OpenAI Codex CLI: 7 incidents in this center's library and 1 CVE in its advisory feed (1 critical), the newest published Apr 14, 2026. Below: what went wrong, what was fixed, and how to use it safely.

What to watch for

The most-downloaded coding agent on npm. Its GitHub Action was taken over through a public issue (an AGENTS.md written by the first pass became trusted input for the second), and Plugin4Shell swapped pinned plugins for malicious ones.

How to use it safely

Update to 0.146.0 or later, treat AGENTS.md and issue text as untrusted, split CI into an unprivileged triage job and a privileged job, and pin plugins by verified commit.

What it can reach

  • Reads attacker-controlled content
  • Runs commands with your permissions
  • Holds API keys and tokens
  • Installs plugins, skills or tools from registries

What went wrong: incidents in the library

Known CVEs

  • CVE-2025-61260 Critical OpenAI Codex CLI runs commands from a repository's MCP configuration
    Apr 14, 2026 · no fixed release in the feed

How many people use it

A high CVE count can mean heavy scrutiny as much as weak engineering, so read the incidents and advisories, not only the number. The counts are what this center has recorded, not every flaw ever found; usage figures are the vendors' and registries' own published numbers.

Sources

Compare it with the others on the Technology watch list