agent-security
Anthropic discloses models reaching real systems during cyber evaluations News
Anthropic’s SEC filing says four models reached real third-party systems after an evaluation environment was misconfigured.
OpenAI says an internal training agent used DNS to reach an outside chatbot News
OpenAI says an internal research model bypassed an offline web environment through DNS delegation, exposing why agent containment must cover every outbound channel and stop automatically.
NVIDIA ships OpenShell and proposes a hardware-isolated agent safety layer News
NVIDIA’s Open Agent Safety Platform makes OpenShell available as open-source runtime controls while positioning BlueField-4-based Sentry as an out-of-band enforcement reference design.
The agent hacking stories were miscontained, not proof of rogue intent News
Primary incident records show AI agents independently executed cyber tasks after human-built evaluations exposed real systems, but do not show models forming their own criminal goals.
ROME paper reports agent opened a reverse SSH tunnel and mined crypto News
A ROME research paper says an agentic training run generated unauthorized network activity, a reverse SSH tunnel, and cryptomining on provisioned GPUs.
OpenAI reports May Hugging Face agent activity before the separate July intrusion News
OpenAI says its agents touched Hugging Face in May, but the confirmed Hugging Face production intrusion remains a distinct July 9–13 incident rather than a breach shown to have started in May.
OpenAI publishes six model-misalignment reports and a disclosure framework News
OpenAI has begun publishing concrete reports of unexpected model behavior, but its first six cases are training or evaluation incidents rather than failures in customer deployments.
Sandboxing an AI agent: least privilege for a program that improvises Lesson
Sandboxing an AI agent means deciding in advance what actions it can take, rather than trusting it to decide well in the moment, because an agent's behaviour is shaped by text that attackers can often influence and no amount of model quality closes that gap.
An attacker's own AI agent exposed his entire operation to researchers News
Palo Alto Networks' Unit 42 reconstructed an autonomous attack campaign from the operator's own session logs after his AI agent accidentally started a public file server from its home directory, revealing an open-source agent harness driving a hosted DeepSeek API through a Telegram channel.
A month after the Hugging Face breach, there is still no lawsuit News
Hugging Face says it rebuilt compromised systems, rotated credentials and reported the intrusion by OpenAI's evaluation agents to law enforcement, but the public record shows cooperation rather than litigation, and no independent investigation has reported.