AGENTS.md files help Codex and similar AI tools understand project-specific instructions, coding conventions, and organizational structures. They can reside anywhere within a Codex container, providing valuable context to AI agents. Like other project configuration files, these instructions are treated as trusted context by the agent. This trust model is by design, but it creates an interesting attack surface when a malicious dependency is able to write or modify these files at build time.
Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments | NVIDIA Technical BlogThis attack path highlights important considerations for the future of agent-assisted development. Extended supply chain risk: Traditional supply chain attacks focus on injecting malicious code directly. In agentic environments, a compromised dependency can also redirect the agent itself, extending familiar supply chain risks into a new dimension, such as injecting subtle delays that cause performance degradation or denial-of-service scenarios. Instruction following under adversarial conditions: When the agent followed injected configuration directives, including instructions to conceal its
Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments | NVIDIA Technical Blog… How to mitigate indirect AGENTS.md injection attacks Strategies for mitigating indirect AGENTS.md injection attacks include automated security monitoring, dependency control, protecting configuration files, monitoring changes, and guardrailing. …
… Although he was happy with the result, Stuyvenberg remains cautious about the security risks this type of agent use creates. “I’m nervous about the scope of what these agents can do, and I’ve revoked a lot of access, and I give it a much more restricted view over my personal digital life,” he says. …
… Most Popular Most Popular The biggest data center ever is becoming a huge problem in Utah Google is launching its own version of OpenClaw If Google can’t make AI agents useful, maybe no one can The 13 biggest announcements at Google I/O 2026 ‘It’s in the air’: Apple TV’s hottest new shows explore d… …
… OpenAI says that the initiative fits into its broader security efforts, including an application security AI agent launched last month known as Codex Security, a cybersecurity grants program that began in 2023, a recent donation to the Linux Foundation to support open source security, and the “Prep… …
… It remains unclear whether OpenAI will continue to offer Codex Security separately or combine it under the umbrella Daybreak initiative. Openai Daybreak Cybersecurity Security Codex Codex for security Gpt-5.5-cyber Report a problem with this article
… However, OpenAI has so far lacked a similar security product. …
… Some attacks succeeded Ex-NSA cyber-boss: AI will soon be a great exploit coder OpenAI tries to build its coding cred, acquires Python toolmaker Astral Infosec community panics as Anthropic rolls out Claude code security checker Joyce quoted security researcher Sean Heelan, who analyzed OpenAI's th… …
… Test every layer before attackers do Security teams log 54% of successful attacks and alert on just 14%. …
… Like Glasswing, Daybreak is a cyber defense effort that will help tech companies find security vulnerabilities in their platforms. …
… OpenAI says Daybreak uses its various AI models, including its specialized security agent Codex. …