The HackWednesday archive
Security analysis, incident lessons, and practical guides for teams working with AI. Search the archive or choose a topic.
AI in Security
Mandiant's July 16, 2026 guidance is a useful warning for defenders: AI can accelerate vulnerability discovery and remediation, but the bigger risk is letting privileged agents into pipelines without deterministic guardrails, scoped identities, and runtime containment.
AI-assisted Awaiting editor review
AI in Security
Microsoft's July 27, 2026 Project Perception launch matters because it reframes AI vulnerability research as a continuous security operations problem with model choice, validation, and remediation controls built into the workflow.
AI-assisted Awaiting editor review
AI in Security
OpenAI's July 21, 2026 disclosure and Hugging Face's July 16, 2026 incident report show that AI security is no longer just about prompt abuse. The evaluation environment itself has become part of the attack surface.
AI-assisted Awaiting editor review
AI in Security
New July 2026 research shows attackers can register the repository and skill names AI agents are likely to hallucinate, turning ordinary package and repo lookup mistakes into remote execution risk.
AI-assisted Awaiting editor review
AI in Security
Claude Code skills can turn repeatable security work into reusable, reviewable workflows for secure code review, secrets triage, dependency risk, threat modeling, incident timelines, and AI governance.
AI-assisted Awaiting editor review
AI in Security
Security teams do not need every product team wiring its own OpenAI, Anthropic, Bedrock, Vertex AI, and coding-agent credentials. A centralized LiteLLM gateway can make GenAI and agentic-code usage more controlled, vetted, auditable, and cost-aware.
AI-assisted Awaiting editor review
Cloud
Starlink-powered in-flight connectivity is changing what passengers expect from airlines, especially on business-heavy routes like Seattle to San Jose. Here is why free Wi-Fi, live flight maps, messaging, and secure browsing should become the new airline and cruise standard.
AI-assisted Awaiting editor review
AI in Security
A new July 2026 agent-security paper argues that defenders are still protecting prompts while attackers are learning to poison the data structures AI agents treat as trusted context.
AI-assisted Awaiting editor review
AI in Security
Anthropic's decision to restore Fable 5 after briefly suspending it over cyber-misuse risk is a useful case study in how frontier AI vendors may start tiering access, hardening safeguards, and treating offensive capability as a live security control problem.
AI-assisted Awaiting editor review
AI in Security
A June 7, 2026 study on AI-powered CI/CD pipelines argues that prompt injection is no longer just a model problem: in real workflows, token scope, untrusted checkout, and trigger design decide whether an agent becomes a supply-chain foothold.
AI-assisted Awaiting editor review
Incident Response
The Miasma worm reportedly led GitHub to disable 73 repositories across four Microsoft organizations. The campaign shows how compromised maintainer identity, CI trust, repository configuration, and AI coding agents can become one self-replicating supply chain.
AI-assisted Awaiting editor review
AI in Security
University of Toronto researchers at CleverHans Lab demonstrated a prototype AI-driven computer worm that can map, test, and compromise heterogeneous enterprise networks in an isolated lab. The important shift is that this class operates outside AI apps and attacks ordinary IT infrastructure.
AI-assisted Awaiting editor review
