A company blog covering security for AI agents, including prompt injection, session behavior analysis and runtime policy enforcement for coding agents. Readers get product announcements alongside technical explanations of how the features are built and the threat models behind them.
Website: https://arcjet.com/blog
A technical newsletter on building, securing, and operating autonomous AI agents, covering retrieval architecture like GraphRAG, reward hacking risks, and LLM inference optimization. Readers get architecture patterns, security perspectives, and engineering guidance for shipping agentic systems.
SilentGrid is an offensive security consultancy whose blog publishes technical write-ups of penetration tests, including AI phone assistant testing, mobile WebView bridge exploits, and LLM agent failure modes. Readers get concrete, hands-on accounts of attack techniques and their root causes.
Weekly cybersecurity newsletter from Sentry covering offensive and defensive security tools and research, including a prompt-injection workbench, a study of abusing free inference, and a disclosed Apple Private Cloud Compute vulnerability. Readers get practical tooling walkthroughs and technical write-ups from applied AI security research.
CyberDesserts is a hands-on cybersecurity newsletter covering application security, pipeline checks, and emerging AI and agent risks. Readers get practical explanations, concrete commands and checks they can run, and analysis of recent OWASP and MCP security developments.
One short email a week with hand-picked newsletters from the index. Free, no spam, unsubscribe anytime.
