‘GhostJacking’ attack turns error logs into indirect prompt injections

Laura FrenchAugust 11, 2026

Attacks targeting Cloudflare, DataDog and Sentry MCP integrations were demonstrated at DEF CON 34.

RESOURCES

Identity
How to Build an AI Governance Framework for Identity
Identity
How to Evaluate and Select Identity and Access Management Tools
Identity
Identity-based attacks: how they work and how to defend against them
Black Hat
Bugcrowd’s Braden Russell on launching Pathseeker
Black Hat
Forcepoint’s Ronan Murphy on securing the data layer AI just set on fire

PODCASTS

Vulnerability Management
Using LLMs for Vuln Discovery – Rishi Sharma – ASW #395
Attack surface management
Attack Surface Management – Matt Lea – CSP #227
Incident Response
Three interviews: system fragility, operational clarity, and Identity for AI agents – Robin Macfarlane, Kyle Sandy, Todd Thiemann – ESW #471
Vulnerability Management
Sci-Fi, PKD, Greatness, Passkeys, AgentBreaker, Rockwell, Flock, Josh Marpet – SWN #605
Supply chain
When AI Commits Felonies – PSW #938

FEATURED

Perspectives Spotlight: Expert Insights

Perspectives Spotlight: Expert Insights

Get daily email updates

SC Media's daily must-read of the most current and pressing daily news

Perspectives

In Brief

More Resources

Binary code on screen with red glowing "BUG" text, symbolizing software malfunction, coding error, or system glitch. Ideal for tech content, debugging, and cybersecurity topics.

Vulnerability Management

Progress LoadMaster bug added to CISA list of exploited vulnerabilities

Steve ZurierAugust 10, 2026

CISA warns of active Progress LoadMaster attacks; patch and investigate now.

Talk to the LLM: How AI exposes ‘pig butchering’ scams

Paul WagenseilAugust 10, 2026

A security researcher is using AI to study and expose long-duration scams that abuse online trust.

AI agent data tools and workflow automation concept with businessman typing on laptop and interacting with digital process interface for artificial intelligence development, integration, productivity

Black Hat: AI isn’t the problem. We are

Paul WagenseilAugust 9, 2026

The obstacles in trying to secure AI use boil down to one issue: We're thinking about it the wrong way.

Glowing fishing hook catching an envelope over a sprawling night city circuit grid dramatic neon lighting phishing cyber security email threat with copy space

Vishing group UNC6671 now focuses on extorting M&A firms

Steve ZurierAugust 7, 2026

Experts urge managed-device logins and audit log monitoring to stop phishing-led cloud data theft.

Bar Lanyado (right) and Eliya Cohen discuss a cost-effective AI agent red teaming method at Black Hat 2026 in Las Vegas. (Credit: Laura French)

Black Hat 2026: Open-source tool makes red teaming AI agents up to 125x cheaper

Laura FrenchAugust 7, 2026

NVIDIA researchers shared the “AgentBreaker” tool and how they tuned an open-source model to perform at frontier level.

AI Agent Workflow: Machine Learning Pipeline DiagramDigital AI Development Process and Data Flow ConceptFeature Engineering and Deployment in AI Ecosystem

Application security

Paperclip authorization bug exploited, leads to control plane takeover

Steve ZurierAugust 6, 2026

Critical Paperclip flaws let attackers seize AI agent platforms, escalate privileges, and execute code.

Punk-rock androids and robots slam-dance.

Black Hat: Agentic anarchy: Why using AI browsers just isn’t worth the risk

Paul WagenseilAugust 6, 2026

Using an AI browser sounds like a good idea until you realize you've just given it the keys to your online identity.

Eric Wallace (left) and Michael Dalton of OpenAI discuss the role of inter-agent communication in its agents’ attack on Hugging Face, at Black Hat 2026 in Las Vegas. (Credit: Laura French)

Black Hat 2026: OpenAI reveals agents planned ‘collective attacks’ via secret ‘message board’

Laura FrenchAugust 5, 2026

OpenAI also said its agents exploited a different JFrog Artifactory zero-day weeks before the Hugging Face attack.

Events