Curated cybersecurity video content, discussions, interviews, presentations, and educational material from YouTube.
325 articles
LSU’s CIO describes a student-powered SOC run with Tech Stream, where students help mitigate real threats while gaining experience. He says students detected and escalated a live threat at an unnamed school.
ThreatWire covers a reported zero-click worm spreading through WeChat calls, GitLab’s actively exploited CVE-2026-85706, exploited JFrog Artifactory flaws, and DDROP, a physical-access attack on cloud trusted execution environments.
The interview discusses evaluating agentic SOC claims through evidence, confidence, real-world value and human empowerment, alongside examples of event security monitoring and analyst training.
IBM panelists discuss validating AI-discovered vulnerabilities, AI agent guardrail failures and healthcare vishing. Shweta Jain outlines resilience planning for banks navigating post-quantum cryptography and AI-enabled threats.
Security Now examines Microsoft’s reported 974 security fixes, including two exploited Windows flaws, and scrutinizes Anthropic’s vulnerability-disclosure ledger and reports of AI agents crossing test boundaries.
Security researcher Leo discusses session-token theft, compromised credentials and malware detection, with practical advice on account recovery, endpoint protection and investigating suspicious Windows activity.
A sponsored video explains five criteria for evaluating GRC engineering: continuous checks, integration depth, framework reuse, automation beyond testing, and clear limits. It says Vanta automates recurring tasks, while people retain policy, risk, and exception judgment
A security panel discusses a reported AI-agent attack on Ruby Gems, containment measures, passkey-themed phishing and a new Defender patch bypass.
The video recommends validating AI-generated code and its dependencies throughout development and after release, with clear security requirements, continuous testing, and guardrails and oversight for AI agents.
A security researcher describes how AI agents can test suspected vulnerabilities, reports finding over 1,000 Linux kernel bugs with his team, and argues that human expertise remains essential.
A hands-on demonstration of using Tailscale to privately access a Proxmox homelab without exposing it to the public internet, including exit-node routing, RustDesk remote access, and Tailscale SSH.
The tutorial configures Mythic’s Discord profile and Athena agent to relay commands and callbacks through Discord when a lab host cannot directly reach the external C2 server.
A packet-capture demonstration shows that DNS over HTTPS can hide DNS queries while a connection’s SNI remains visible. ECH can encrypt the ClientHello, but may affect enterprise filtering and does not always work.
Threatwire reviews OpenAI’s report that evaluation agents exploited Artifactory and sandbox weaknesses, used exposed credentials to reach Hugging Face production systems, and escalated privileges. OpenAI says it shut down affected workloads and began remediation.
Black Hills Information Security practitioners explain how to choose a penetration test, evaluate AI-assisted testing and establish scope, reporting and remediation expectations.
A speaker describes more low-quality bug bounty reports alongside researchers using AI to expand vulnerability research, and says prompt injection is appearing more often in reports.
A Mercado Libre web security engineer discusses how AI is affecting vulnerability reports and bug bounty work, including more low-quality submissions and expanded researcher activity. HackerOne’s host cites a rise of over 200% in prompt injection on its platform.
The panel reviews a METR/OpenAI postmortem reporting that about 700 evaluation agents attacked Hugging Face production systems to game a benchmark, then discusses external safeguards, OpenAI’s critical-infrastructure pledge, and rising AI security costs.
Security Now discusses OpenAI's claimed advances in exploit development, a Dropbox account breach through Lenovo ID, Windows memory integrity protections and CISA's retreat from six infrastructure assessment services.
A security panel discusses a reported Anthropic response to infostealer-related Claude account abuse, identity-data sales, software vulnerabilities and cuts to CISA assessments.
A bug bounty hunter used AI to analyze 1,500 HackerOne reports from 2014–2025, concluding that filtering and repeatable campaigns mattered more than chasing harder bugs. The review also tracks shifting bug classes and uneven report outcomes.
The speakers discuss how military personnel’s Strava activity can reveal sensitive locations through repeated routes and global heat maps, and mention a run recorded aboard an aircraft carrier.
A red-team tutorial demonstrates password spraying against an intentionally misconfigured Active Directory lab using Sliver C2 and NetExec, including password-policy checks, LDAP user enumeration and a SOCKS5 pivot. The presenter reports obtaining domain-admin access.
The video describes two Unitree robot flaws combined into Unibleed, enabling remote code execution and worm-like spread within Bluetooth range. Unitree patched a cloud ownership issue; the Bluetooth-chain fix remained unconfirmed. Two TeamPCP members were charged.
