What changes when software acts on its own. AI agent identity, prompt injection, model risk and the controls security teams need before agents reach production.
148 posts, newest first. Page 1 of 5.
Tags in this track:AI SecurityAI Agent SecurityAgentic AIMachine IdentityPrompt InjectionLLMAIMCP
Latest in AI Security & Agents
Superintelligence became federal vocabulary and a signed industry pledge in one week. The systems did not change. Here is what the label means in your stack, and the 12-month checklist that matters more than the name.
Read the article
AI removed the writing bottleneck in SaaS onboarding email. The constraint moved to product event data, and the small teams winning on activation and conversion fixed that first.
OpenAI has notified more than 100 organizations that its AI agents may have accessed their systems without authorization. The cause was not a smarter attacker. It was exposed credentials, legacy token endpoints, and agents nobody was watching. What happened and what to do this week.
Anthropic, OpenAI, Google, xAI and DeepSeek all retired or scheduled model retirements in 2026, and some old names quietly served new models. Here is what changed, why it matters, and how to use the AI Models lifecycle page to build a model-retirement calendar.
Microsoft's Defender team catalogued 31 companies across 14 industries embedding hidden instructions in "Summarize with AI" buttons to bias assistant recommendations. One sold web security software. After fifteen years in security, here is why AI visibility became a governance problem.
AI agents now act with real credentials, and agent incidents have started. The Agent Security Map found that of 47 vendors checked, 11 publicly document a kill switch. Here is what that means and how to use the matrix to question vendors.
On September 20, Amazon blocked Meta's new Muse AI agent from its store. That fight signals where commerce is heading: the shopper is becoming an AI agent. How agents discover, compare, and buy in B2C and B2B, and why product discovery is now your most important marketing problem.
In 2026, Cisco bought Astrix, SailPoint bought Entro, Okta bought Permiso and Cyera bought Oasis. The Agent Security Map deals ledger tracks all 30 deals with SEC-filed prices and sources, and shows a security buyer how to check a vendor's ownership before the next call.
America.gov launched on September 29, 2026 as a single AI front door to federal services, drawing on 29,000 government websites. What it does today, how to use it well, where it falls short, and what other countries should take from it.
Jensen Huang declared AGI had arrived in a post that ended with "400K GPUs coming online next." That is not a scientific claim. It is a capital request with a headline attached. 2026 was remarkable. It was not the year general intelligence arrived.
Model providers solved the machine half of agent authentication in 2026. The half nobody solved is attribution: no provider can tell you which human authorized what your agent did.
Zero data retention is not a setting, it is a contract term with a scope. The gap between what founders think ZDR covers and what it contractually covers is wide enough to fail an enterprise review.
Most founders think the EU AI Act is the model provider's problem. If your output is used in the EU, you carry obligations of your own, and the enforcement machinery went live in August 2026.
OpenAI, Anthropic, and Meta each confirmed an agent incident against a real target in three weeks. The labs are right that it was a test. The capability is not.
An AI model manufactured fake identities to socially engineer a real maintainer, then edited its tracks when challenged. The request failed. The threat model should not.
Self-propagating instructions can spread through ordinary agent memory. Isolated agents with conflicting goals wrote malware to sabotage each other.
MCP's July 2026 spec rewrite went stateless and made Client ID Metadata Documents the standard, not audience-bound tokens, which have been mandatory since mid-2025. What actually changed since December 2025, and the checklist that replaces the old one.
Machine identities now outnumber human ones 109 to 1, and four 2026 acquisitions worth $26.6B prove vaults can't keep up. What ephemeral secrets and workload identity replace them with.
Engineering teams resist AI initiatives over career anxiety and loss of control, not technical doubts. What actually worked leading teams through this at LoginRadius and GrackerAI.
Most companies ask how to help people get better at using AI. The more consequential question is which human and organizational capabilities become more valuable every time AI becomes more capable.
Most teams shipped AI agents without ever bounding what they can reach. The fix is a 1990s forward proxy, and an allowlist alone will not save you.
MIT found 95% of generative AI pilots produce no measurable return. After running AI agents in production for hundreds of B2B SaaS customers, here are the three warning signs I wish I'd caught earlier.
CPU cache is the fast memory between the cores and main memory. What L1, L2, and L3 each do, why cache lines are 64 bytes, and when more cache actually makes a processor faster.
The AI observability market split into four segments (infra telemetry, dev tooling, runtime security, autonomous remediation) with a wave of 2025-2026 acquisitions behind it. None of them own whether an agent behaved correctly.
Prompt engineering is overrated. In 2026 the AI products that ship and stick win on context, evals, data, and workflow. Here is the stack that actually matters.
A leaked static key is a disaster; a five-minute token is mostly a shrug. Here is the credential lifecycle that gets AI agents from 24-hour tokens to ephemeral ones.
Your data isn't ready for AI, and that's good news. It means you found the problem before you built on it. What LoginRadius, GrackerAI, and LogicBalls taught me about the gap between organized data and AI-ready data, plus the 2025 numbers on why it sinks most projects.
Shadow AI is an employee pasting into ChatGPT. A shadow agent holds real credentials and acts on its own. That is a different, and bigger, problem.
Mandiant ranked voice phishing the second most common initial infection vector of 2025. In the same window, thousands of businesses handed their phone lines to AI agents. Those two facts are related, and the security implications run in both directions.
MCP is Anthropic’s open standard for connecting AI agents to your tools and data. Here is what it actually is, how it differs from a REST API, and a clear rule for when to use each in 2026.
Your AI security review passed and still missed the real attack surface. EchoLeak, over-permissioned agents, shadow AI: the AI-specific vectors most CISOs never test for, and the five moves that close them.
New writing on identity, AI security, and building software, delivered when it ships. No tracking pixels, no funnels, unsubscribe with one click.
