Agentic AI
Verified developments, reporting, and emerging signals in agentic ai.
Show HN: AegisKernel – Zero-trust deterministic security runtime for AI agents
When AI Agents Commit Breaches, Humans May Not Be Held Liable
AWS Security Agent (now part of AWS Continuum) exploited 33 of 37 new real-world CVEs
Is AI pentesting as good as a human pentester?
Show HN: Netlumi – Cloud and AI agent security with auto-remediation(Live demo)
What Survives Self-Evolution: Provenance Marks in Copied Agent Harnesses
Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization
AI agents aren't 'going rogue.' Frontier labs are skipping security basics
From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)
The Blind Spots of Agentic Pentesting and How to Close Them
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
Beyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
Visual Studio Copilot and SSMS Remote Code Execution (CVE-2026-103572)
CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
Sandbox vulnerability gives rogue AI agents a path to escape and leak data, research says
Defenders Reluctant to Deploy Agentic AI as a Cybersecurity Tool
Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher
Standing, Not Truth: Who May Say What About Whom in Agentic Selection
ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?
SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models
I build an open-source runtime security layer for AI agents – Let's break it
AI Browser Agents: SEO, Security and Implementation Playbook for 2026
AI Agent Security: Six Controls from Nine Real Incidents
How to keep AI agents within their permissions
Could LLM Watermark Detection be Public?
CVE-2026-69435 Azure SRE Agent Elevation of Privilege Vulnerability
Rein Security Raises $25 Million to Guard AI Agents at Runtime
Chinese Hacker Deployed AI in Campaign Against South Korean Banks
Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery
GROB: A Multi-Agent Architecture for Public-Trace Investigation of Candidate Agentic Activity
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
Australian Gov't Weighs Mandatory AI Incident Reporting
Show HN: Leaks.md – anonymous, encrypted whistleblowing for AI agents
Secure-CUA: Controlling Untrusted Influence in Computer-Use Agents
OpenAI “rogue” agent activities found on Wikimedia projects
SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations
Google's PageBreak AI Agent Finds 500 Flaws in Its Web Apps
Identity-aware AI data agents with AWS Lake Formation and Trusted Identity Propagation
South Korean officials believe AI agents were used to hack several banks
Apple to Tighten Full Disk Access Controls in macOS Amid AI Risks
Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering
Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security
Wikipedia operator says OpenAI’s ‘rogue’ bots may be linked to a May outage
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair
AI Agents Are Disrupting Open Source Security Disclosure
Agentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search
The AI Exposure Brief
A five-minute weekly briefing for CISOs, CIOs, AI governance leaders, and enterprise security teams.
Verified developments. Emerging agent risks. Regulatory changes. Practical control questions.
No spam. Unsubscribe anytime.