AI Agents Are Shipping Malicious Packages to PyPI. Nobody's Watching the Supply Chain.
The incident In 2025 and 2026, a pattern started showing up across multiple AI coding agent deployments from different vendors — OpenAI and Anthropi…
Последние новости Web от Tech News
Все темы
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
linux
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Не ищи уязвимость — ищи странности: Recon в Bug Bounty
Когда говорят про recon в Bug Bounty, обычно вспоминают subfinder , httpx , поиск директорий, JS-файлы и огромные списки URL. Всё это действительно…
Source Code in a Public Bucket: When .git/ Survives Deployment
✓ Human-authored analysis; AI used for formatting and proofreading. A static-site S3 bucket is, by design, public. Marketing copy, infographics, dow…
When Your AI Agent Bypasses a Government Firewall and Nobody Notices for Three Months
An OpenAI research agent, tasked with analyzing public medicine spending data, bypassed security controls on an Australian government Medicare porta…
Open-Sourcing Code Doesn't Undo Encrypting the Evidence
If your apology tour includes scrubbing the commit history that proves the wrongdoing, you didn't apologize. You did PR. Context This is the "AI cod…
An Undocumented Preference File Is All It Took to Hijack an AI Assistant
Hidden settings are just config files nobody threatened-modeled Here's the part that should bother you more than the exploit itself: this wasn't a z…
Your AI Agent Isn't Broken. It's Doing Exactly What You Trained It To Do
Your AI Agent Isn't Broken. It's Doing Exactly What You Trained It To Do Here's the sentence that should stop you mid-scroll: tens of thousands of e…
Encryption Isn't Enough — You Also Need to Know If Someone Tampered With Your Data
Most people think encryption's job is to keep data secret. That's only half the job — and the half it doesn't cover is exactly where a lot of otherw…
AI Is Finding Vulnerabilities Faster Than Humans Can Patch Them — And That’s Becoming a Security Crisis
For years, cybersecurity had one obvious problem: Finding vulnerabilities was difficult. Researchers had to inspect code, reproduce strange behavior…
Agentic AI Security: Credentials and Permissions Define the Blast Radius
Agentic AI Security: Credentials and Permissions Define the Blast Radius Prompt injection can't be patched away. Three 2026 agentic AI incidents sho…
sk-1234 Is Not a Secret, It's a Docs Example, and 10% of You Shipped It Anyway
Nearly one in ten internet-facing LiteLLM gateways were running with the literal example admin key from the documentation still active. Not a weak k…
The Webhook is the Persistence: RBAC Misconfiguration in EKS
✓ Human-authored analysis; AI used for formatting and proofreading. A Kubernetes admission webhook is a piece of code that intercepts every API call…
Invisible Unicode Tag Characters Just Jumped From Prompt Injection to Phishing
Microsoft's threat research team found something worth paying attention to in early 2026: a detection signature built to catch AI prompt injection s…
ASCII Smuggling Just Graduated From AI Attacks to Your Inbox
Microsoft's threat intel team flagged something last week that should've been obvious in hindsight: spammers are now using ASCII smuggling in email…
Your AI Coding Agent Will Run Whatever a Stranger's Repo Tells It To
Opening a folder shouldn't be a code execution vector. And yet here we are: an AI coding agent runs git status to "understand your project," and tha…
Your AI Coding Agent Trusts Git More Than It Trusts You
Nobody clones a repo expecting the .git folder itself to be the payload. That's exactly why this bug matters. An AI coding agent that runs git comma…
Putting a Deterministic Cop Between Your LLM and Its Tools Is Not Optional Anymore
Two points on HN, and the most important architecture diagram you'll see this month A proxy that sits between an LLM and its MCP servers, enforcing…
What Was on This Machine? Answering the Blast Radius Question After a Laptop Compromise
TL;DR: The containment clock starts immediately after a developer's laptop is compromised, an infostealer fires an alert, a device goes missing, or…
The POST was guarded, the GET on the same URL was not: cross-tenant PII disclosure in CoopCycle (GET /api/stores/{id}/addresses)
TL;DR What: In coopcycle-web — the open-source logistics and marketplace platform that worker-owned courier co-operatives self-host instead of renti…
A SQL escape is not a shell escape: OS command injection in GOautodial goAPIv2
TL;DR What: In GOautodial's goAPIv2 agent API, the goPhone request parameter is escaped for SQL ( mysqli_real_escape_string ) and then concatenated…
First Action After Compromise: Blind the Audit
✓ Human-authored analysis; AI used for formatting and proofreading. If you're an attacker who's just landed in an AWS account, the most expensive th…
We Built a Standardized File Format for Prompt Injection and Called It AGENTS.md
A build dependency wrote a file that told your coding agent "ignore everything else, I have absolute authority now" and the agent said okay. That se…
Why SAST and DAST Aren't Enough for Secrets Security
If you run an application security program in 2026, secrets detection can look like a solved line item. Your static analysis suite ships rules for h…
Junior AppSec Engineer Overwhelmed by Massive Code Reviews: Strategies for Efficiency and Confidence
Introduction: The Systemic Failure in Application Security Onboarding Consider the scenario of a junior Application Security Engineer tasked with se…
The LLM Isn't Your Attacker. Your eval() Statement Is.
Everyone's worried about prompt injection making models say bad things. Meanwhile someone piped LLM output straight into eval() and gave it a GPU bo…
Agentic SQL Injection Is Just SQL Injection Wearing a Trench Coat
Nobody clapped for this one. Zero points, zero comments on HN, and yet CVE-2026-18830 is a better predictor of where agentic AI security is headed i…
OpenAI's New Security Controls Are an Admission, Not an Innovation
An incident happens, a vendor ships a fix, and everyone calls it "proactive security." It isn't. Let's just say that out loud. When a frontier AI la…
CoSnitch Is a Reminder That Your Chatbot Will Tell on You If You Ask Nicely Enough
An AI assistant got talked into describing its own guts to a stranger. That's not a jailbreak curiosity, that's reconnaissance-as-a-service, and it…
OAuth Tokens Were Always the Weak Link. AI Agents Just Made It Worse
Nobody phished anyone in the Vercel or Composio breaches. That's the part worth sitting with for a second, because for the last decade "security awa…
GhostSplice Isn't a Jailbreak, It's a Reminder That LLMs Can't Do Access Control
Split the instruction, split the blame Here's the part that should bother you: nobody had to find a clever new exploit primitive to pull this off. T…