#ai-agents
89 stories taggedai-agents · page 6 of 6.
AI Web Agents Have No Reliable Prompt Injection Defenses, Benchmark Finds
Researchers ran 3,168 adversarial tests against GPT-5 and Gemini-powered agents. The 'Robust Behavior' outcome — agent completes task, attacker gets nothing — never appeared.
LangGraph Patches Three Bugs, Including an SQLi-to-RCE Chain in Self-Hosted Agents
The framework underpinning a wave of multi-agent AI deployments shipped fixes for a flaw chain that let attackers pivot from SQL injection to code execution on self-hosted nodes.
Researchers Turn OpenClaw Into a Confused Deputy With Hidden Prompts
Two teams show the self-hosted AI agent will execute attacker instructions smuggled inside contacts, location pins, and other benign-looking inputs.
Six Things SRE Teams Demand Before Handing Anything to an AI Agent
Observability gaps, missing guardrails, and opaque reasoning are the real blockers — not the AI itself.
AI Agents in Phishing Tests: Risks and Failures Exposed
Autonomous AI agents can be tricked into leaking sensitive data, highlighting configuration issues in security frameworks.
Microsoft Expands Its Agentic AI Failure Taxonomy With Seven New Attack Classes
From inter-agent trust escalation to MCP plugin abuse, the updated taxonomy surfaces threat categories that didn't exist — or weren't well-understood — when Microsoft published its first version.
$7M Says Autonomous Agents Can Fix the Identity Sprawl Problem
Offroad exits stealth with a bet that AI-driven security agents can manage what platform teams stopped being able to track manually — machine identities, third-party app permissions, and the rest of the non-human identity mess.
Microsoft Cages the Agent: MXC, MDASH, and the Push to Govern Autonomous AI at Runtime
Microsoft is shipping a dedicated containment environment for agentic AI workloads, alongside open-source governance frameworks and expanded vulnerability-scanning capabilities — all aimed at reining in what autonomous coding agents can actually do.
Someone Finally Tested 100 AI Agents for Security. Here's the Framework They Used.
A new evaluation methodology ranks AI agents by vulnerability, blast radius, and defensive posture. The results are a useful corrective to vendor claims.
The Linux Foundation Wants DNS to Be the Phone Book for AI Agents
DNS-AID proposes using existing DNS infrastructure for agent discovery — no new directories, no vendor lock-in, no new protocols to trust.
French Startup Edamame Builds Runtime Watch for AI Coding Agents
The platform uses host telemetry and AI analysis to flag intent drift, secret theft, and supply-chain interference — in real time, before the damage lands.
You Can't Audit What You Can't See: The Agent Governance Hole Nobody Wants to Talk About
Enterprises are shipping AI agents into production without inventories, without trace pipelines, and without a coherent answer to a basic question: what is this thing actually doing?
Treat the Model Like a Threat: Why AI Agent Security Needs a Systems Overhaul
A paper from researchers at Google and two US universities argues that prompt-level defences and alignment tuning are structurally inadequate for securing autonomous AI agents — and that enterprises should start treating the model itself as an untrusted component.
AI Agent Identities Are Redrawing Enterprise IAM Budgets
New Omdia research finds that the rapid spread of AI agent deployments is forcing organisations to treat non-human identities as a distinct governance category, with budget implications that traditional identity and access management frameworks were not designed to absorb.