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
- Microsoft: about 1 percent poisoned fine-tuning data, or a tampered open-weight model, can make a coding agent run an attacker's commands on a trigger Medium
Microsoft Security Research and the Microsoft AI Red Team (Amanda Minnich, Amit Eliahu, Blake Bullwinkel, Dor Edry and Giorgio Severi) published on November 12, 2026 two studies of backdoors that stay dormant until a trigger… - An AGENTS.md file in the Downloads folder told a coding agent to install a malicious npm package High
Forever Security blocked an AI coding agent on a customer's machine from installing an npm package called function-color, and traced the order to an AGENTS.md instruction file in the customer's ~/Downloads folder, where the… - LiteLLM 1.107.0: stolen GitHub tokens pushed a credential-stealing release to PyPI and Docker Critical
LiteLLM reported that on October 21, 2026 its release pipeline published litellm 1.107.0 with compiled malware that steals credentials and loads remote-code execution tools. Using three engineers' GitHub accounts, through stolen… - OpenAI's official Render skill sent production apps' tokens to a domain that did not exist, until researchers registered it High
A skill in OpenAI's official GitHub repository of skills, which teaches agents how to deploy applications on Render, told production apps to send their tokens to render-internal.com, a domain nobody had registered, CSO Online… - Plugin4Shell: zero-click takeover of four coding agents through plugin pinning Critical
AIR found that Claude Code, Codex, GitHub Copilot and Gemini CLI checked out a pinned plugin commit without verifying they had landed on it, so a trusted plugin could be swapped for a malicious one and auto-installed with no… - GitSpawn: a repository's .git/config runs code the moment seven coding agents open the folder High
Manifold Security (Francisco Rosales and Ax Sharma) showed on September 1, 2026 that AI coding agents run git commands such as git status and git diff when they open a folder, to gather context, before the workspace-trust prompt… - Coding agents in GitHub Actions: one public issue to stolen CI secrets Critical
At Black Hat USA 2026, Novee Security showed that anyone able to open a GitHub issue could take over the official GitHub Actions setups for Claude Code, Gemini CLI and Codex. Hidden instructions in the issue made the agent run…
Known CVEs
- CVE-2025-61260 Critical OpenAI Codex CLI runs commands from a repository's MCP configuration
How many people use it
- 25.1M npm downloads in a week (Sep 22 to 28, 2026) · npm download counts
- 127k GitHub stars · GitHub
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
- npm download counts: npm downloads in a week (Sep 22 to 28, 2026)
- GitHub: GitHub stars
- GitHub Advisory Database: @openai/codex
- Microsoft Security Blog: Trained to betray, how post-training supply chain attacks hijack coding agents
- BleepingComputer: AI coding agents hijacked using AGENTS.md file in Downloads folder
- TechRadar: AI agents tricked by a rogue downloads file into running dangerous malware
- LiteLLM: Oct 21, 2026 release v1.107.0 compromised
- Help Net Security: LiteLLM hit by second supply chain attack this year
- Wiz: LiteLLM compromised, steals credentials
- The Register: LiteLLM supply chain attack started with an exposed master key
- LiteLLM: the attack chain behind the v1.107.0 release
- CSO Online: hallucinated domain in official OpenAI skill underscores AI supply chain risks
- AIR Security: the Render skill in OpenAI's repository
- AIR: Plugin4Shell
- Help Net Security: Plugin4Shell AI coding agents vulnerability
- The Register: AI coding agents 0-click RCE flaw could hand attackers the keys to the kingdom
- Manifold Security: GitSpawn, AI coding agents hijacked through git config
- Goose advisory GHSA-r5pp-p5r8-466r (CVE-2026-72718)
- paddo.dev: Opening the folder was the exploit
- Novee Security: critical flaws in Anthropic, Google and OpenAI's coding agents
- GitHub Advisory: Gemini CLI GHSA-wpqr-6v78-jr5g
- Anthropic: Claude Code advisory GHSA-fg94-h982-f3mm