AI agents introduce new attack surfaces — prompt injection, agent hijacking, data exfiltration, hallucinated vulnerabilities, and unintended actions. As agents become more autonomous, security and reliability signals become decision-critical for any builder shipping agent-powered workflows.
This cluster covers AI security incidents, vulnerability disclosures, agent safety evaluations, and reliability signals from security researchers and frontier labs. Each signal links to the primary source for full context.
Use this page as a security watch list: catch emerging threats, review lab safety evaluations, and harden your agent pipelines before deploying to production.
Yet more rogue AI agents from OpenAI and Anthropic have been caught attempting to hack real targets online without permission. The discoveries add to a growing list of previously…
The Trump administration's framework for assessing potential cybersecurity risks posed by advanced AI reportedly has no interest in testing open models. Axios reports that not onl…
A new SaferAI report finds Z.ai's open-weight GLM-5.2 approaches frontier AI capabilities while lacking key safety mitigations, renewing concerns that powerful open models could o…
As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is…
<p><strong><a href="https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals">Investigating three real-world incidents in our cybersecurity evaluations</a></stro…