Cor E

I'm an automation engineer, pentester, dev, network arch & *nix guru I curate & create my own content. AI helps draft/edit some posts — final review & editorial judgment are mine.

Tokyo, Japan Joined on Mar 25, 2026 https://skyblue-soft.com/blog/

Work

Freelance Dev, Pentester, Automation Work, Network Architect - Founder of Sentinel-Proxy AI Firewall

Cor E

Oct 31

A Poisoned AGENTS.md in ~/Downloads Hijacked Codex and Claude Code. Here's Where the Scrub Step Fits.

#security #ai #llm #appsec

5 min read

Want to connect with Cor E?

Create an account to connect with Cor E. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Cor E

Oct 31

Your AI Agent Read an Email and Ran Commands. No Vulnerability Required.

#security #ai #llm #sentinel

6 min read

Cor E

Oct 28

Your AI Gateway Logs Are Now a Credential Store, Whether You Meant That or Not

#security #ai #devops #appsec

4 min read

Cor E

Oct 28

When the Agent Edits Its Own Monitor: What OpenAI's Two Disclosed Incidents Mean for Your Tool Layer

#security #ai #appsec #sentinel

5 min read

Cor E

Oct 25

The "AI Attack" Headline Is Hiding a Very Boring Credential Leak

#discuss #security #ai #appsec

4 min read

Cor E

Oct 24

Prompt Injection in HTTP Headers: What 217M Web Responses Show

#security #ai #llm #sentinel

5 min read

Cor E

Oct 23

A $75,000 Invoice, a Fake CFO Approval, and Why Prompt-Level Defenses Aren't Enough

#security #ai #llm #appsec

5 min read

Cor E

Oct 23

The Agents Didn't Go Rogue. Somebody Forgot to Build the Fence.

#discuss #security #ai #appsec

3 min read

Cor E

Oct 17

Your Decompiler Output Is Now an Attack Surface

#security #ai #llm #appsec

4 min read

Cor E

Oct 17

AI Agents Are Shipping Malicious Packages to PyPI. Nobody's Watching the Supply Chain.

#security #ai #appsec #devops

5 min read

Cor E

Oct 13

Log Files Are Untrusted Input - A Red Team Found Out the Hard Way

#security #llm #ai #appsec

6 min read

Cor E

Oct 13

An AI "Example" Filed a Real Police Report. Nobody Noticed for Two Months.

#ai #llm #security #cybersecurity

3 min read

Cor E

Oct 11

UAC-0099's GuardBreaker Trick: Poisoning Malware With a Nuclear Weapons Prompt to Dodge AI Analysis

#security #cybersecurity #ai #llm

6 min read

Cor E

Oct 11

$300 Says Your Bug Bounty Program Isn't Actually About Security

#discuss #security #ai #appsec

3 min read

Cor E

Oct 8

One Argument-Injection Bug Took Down OpenAI Codex at Pwn2Own. Here's the Detection Gap.

#security #ai #llm #appsec

5 min read

Cor E

Oct 8

15,465 Public MCP Servers, Zero Vetting - What That Means for Your Agents

#security #ai #mcp #cybersecurity

6 min read

Cor E

Oct 6

Apple Just Admitted the Permission Model Was Never Built for Agents That Read Everything

#ai #security #appsec #cybersecurity

3 min read

Cor E

Oct 5

Gemini Wants the Keys to Your Mac. We've Seen This Movie Before.

#discuss #security #ai #appsec

3 min read

Cor E

Oct 5

JSFuck in Your Inbox: How an Old JS Obfuscation Trick Beat an AI Agent's Guardrails

#security #ai #llm #cybersecurity

5 min read

Cor E

Oct 4

13,000 Leaked Screenshots Show Why Agentic Tool Output Needs a Firewall, Not Just a Prompt

#security #ai #cybersecurity #sentinel

5 min read

Cor E

Oct 4

Websites Are Learning to Gaslight Bots, and Honestly, Good

#security #ai #llm #appsec

3 min read

Cor E

Oct 4

We Shelved a Model for Lying and Attacking Supply Chains. Let's Sit With That.

#ai #security #cybersecurity #machinelearning

3 min read

Cor E

Oct 2

JadePuffer Isn't the AI Apocalypse, It's Just Ransomware With Better Scripting

#security #ai #cybersecurity #devops

3 min read

Cor E

Oct 2

We Gave AI Agents Shell Access, Now We Need AI to Watch Them

#security #ai #appsec #cybersecurity

3 min read

Cor E

Sep 29

DNS Tunneling Is Older Than Your Sandbox, and It Just Proved It

#security #ai #llm #cybersecurity

3 min read

Cor E

Sep 28

When an OpenAI Agent Touched Medicare's Servers: Three Months of Silence and a Senate Summons

#security #ai #llm #cybersecurity

6 min read

Cor E

Sep 28

Salesbleed Isn't a Salesforce Bug. It's What Happens When Agents Trust Their Inputs

#security #ai #llm #appsec

3 min read

Cor E

Sep 28

10 Open-Source Prompt Injection Detectors, 629 Real Attacks, One Passed 51%

#security #ai #llm #machinelearning

5 min read

Cor E

Sep 27

When Your AI Agent Bypasses a Government Firewall and Nobody Notices for Three Months

#security #ai #appsec #cybersecurity

6 min read

Cor E

Sep 25

Grok's Wallet Drained by Morse Code: Inside an AI Agent Goal Hijack

#security #ai #llm #cybersecurity

5 min read

Cor E

Sep 25

Open-Sourcing Code Doesn't Undo Encrypting the Evidence

#security #ai #appsec #cybersecurity

3 min read

Cor E

Sep 25

An Undocumented Preference File Is All It Took to Hijack an AI Assistant

#security #ai #cybersecurity #appsec

3 min read

Cor E

Sep 24

Plugin4Shell: When Your AI Coding Agent Auto-Updates Straight Into RCE

#security #ai #cybersecurity #devops

5 min read

Cor E

Sep 24

One Extension, Five Browsers, Zero Malicious Code: The Agent Hijack Nobody Priced In

#security #ai #llm #appsec

3 min read

Cor E

Sep 24

Your AI Agent Isn't Broken. It's Doing Exactly What You Trained It To Do

#security #ai #appsec #devops

3 min read

Cor E

Sep 17

Your Calendar Invite Just Ordered Cupcakes: The Smart Home Agent Security Gap Nobody's Watching

#security #ai #llm #cybersecurity

5 min read

Cor E

Sep 13

Your Test Environment Is Not a Sandbox If It Has Internet Access

#security #ai #llm #cybersecurity

3 min read

Cor E

Sep 13

Iran Used Claude to Target US Navy Ships. Here's the Jailbreak Pattern Nobody Caught

#security #ai #llm #cybersecurity

6 min read

Cor E

Sep 13

1.8 Million APKs Later, We Should Talk About What "AI Agent" Actually Means in a Threat Model

#security #ai #cybersecurity #appsec

3 min read

Cor E

Sep 13

An AI Agent Swarm Just Red-Teamed a Package Registry Without Asking Permission

#security #ai #appsec #cybersecurity

3 min read

Cor E

Sep 13

sk-1234 Is Not a Secret, It's a Docs Example, and 10% of You Shipped It Anyway

#security #ai #llm #appsec

3 min read

Cor E

Sep 10

Model Distillation Is Just Espionage With Better PR

#security #ai #llm #cybersecurity

3 min read

Cor E

Sep 10

Six Hours, Thousands of Credentials, and Zero Surprise

#security #ai #cybersecurity #appsec

3 min read

Cor E

Sep 9

Invisible Unicode Tag Characters Just Jumped From Prompt Injection to Phishing

#security #ai #cybersecurity #appsec

6 min read

Cor E

Sep 8

CVE-2026-85620: When Your MCP Server's Allowlist Parser Isn't the One Actually Parsing SQL

#security #ai #cybersecurity #devops

5 min read

Cor E

Sep 8

18,000 Posts Later: What OpenAI's Rogue Wiki Incident Teaches About Agentic Tool Abuse

#security #ai #llm #agentic

6 min read

Cor E

Sep 6

ASCII Smuggling Just Graduated From AI Attacks to Your Inbox

#security #cybersecurity #ai #appsec

5 min read

Cor E

Sep 6

Your AI Coding Agent Will Run Whatever a Stranger's Repo Tells It To

#security #ai #appsec #devops

3 min read

Cor E

Sep 6

Three AI Labs Admit Their Agents Cheat and Break Into Things. Nobody Blinked.

#security #ai #llm #cybersecurity

3 min read

Cor E

Sep 3

Your AI Coding Agent Trusts Git More Than It Trusts You

#security #ai #appsec #cybersecurity

3 min read

Cor E

Sep 3

We Gave an AI Your Inbox, and It Fell For the Oldest Trick in the Book

#ai #security #llm #cybersecurity

3 min read

Cor E

Sep 3

Putting a Deterministic Cop Between Your LLM and Its Tools Is Not Optional Anymore

#security #ai #llm #appsec

3 min read

Cor E

Aug 29

Three AI Agents Walk Into a Codebase, and Only One Walks Out

#ai #security #llm #cybersecurity

3 min read

Cor E

Aug 28

White Text, Real Instructions: How Invisible HTML Hijacks AI Email Summaries

#security #ai #llm #cybersecurity

5 min read

Cor E

Aug 28

We Built a Standardized File Format for Prompt Injection and Called It AGENTS.md

#security #ai #appsec #devops

3 min read

Cor E

Aug 28

700 Rogue AI Agents Escaped a Sandbox and Coordinated an Attack on Hugging Face

#security #ai #cybersecurity #devops

5 min read

Cor E

Aug 27

The LLM Isn't Your Attacker. Your eval() Statement Is.

#security #llm #appsec #devops

4 min read

Cor E

Aug 27

Grok's Zero-Click Chat Leak: When Encrypted Text Becomes a Trusted Instruction

#security #ai #llm #cybersecurity

6 min read

Cor E

Aug 24

Agentic SQL Injection Is Just SQL Injection Wearing a Trench Coat

#security #ai #llm #appsec

3 min read

Cor E

Aug 22

OpenAI's New Security Controls Are an Admission, Not an Innovation

#security #ai #appsec #machinelearning

3 min read

4 Week Community Wellness Streak

2 Week Community Wellness Streak

1 Week Community Wellness Streak

Writing Debut

Want to connect with Cor E?