⌁AI·CYBER·BRIEF▌

#Prompt Injection

Vulnerabilities6 min read

ChatGPT preview flaw let attackers bypass Lockdown Mode and quietly send chats out; OpenAI has fixed it

Check Point found a gap in ChatGPT's HTML preview sandbox that defeated Lockdown Mode and could leak chat history and files. OpenAI says it deployed a fix by September 18, 2026.

OpenAIChatGPTLockdown Mode
AI Threats6 min read

A planted AGENTS.md file in Downloads can turn your AI coding agent against you

Researchers say a web page can drop an instruction file into Downloads; a coding agent started there may follow it. Don't run agents from Downloads.

AI coding agentsPrompt InjectionOpenAI Codex
Vulnerabilities8 min read

Built-in browsers in Codex and VS Code can expose local files; fixes still pending

Researchers found flaws in the embedded browsers of five AI coding tools. Cursor and Copilot are fixed; Codex and VS Code were still unpatched on October 29.

EMBRACEOpenAI CodexVS Code
Vulnerabilities6 min read

AI coding agents keep installing archived MCP servers that will never get security fixes

Glow Labs found coding agents installing retired @modelcontextprotocol reference servers from training data. One has an unpatched prompt-injection-to-RCE flaw.

MCPModel Context ProtocolMCPhantom
AI Threats7 min read

"Prompt adware": a Codex jailbreak kit quietly rewrites the AI agent's own instructions

Check Point found a popular jailbreak bundle for OpenAI Codex that plants a permanent ad in the agent's global instructions. Small harm, new kind of AI supply-chain risk.

OpenAI CodexPrompt AdwareCheck Point Research
Vulnerabilities11 min read

From SELECT to sysadmin: SQL Server's Copilot enforced "read-only" with a regex

A BlueHat Asia talk shows how Copilot in SQL Server Management Studio could be steered past its "read-only" mode, and how one database owner's notes became an attack on admins.

AnalysisPrompt InjectionMicrosoft
Vulnerabilities8 min read

Meta patched the Muse Mac zero-day in a day — but there is no version number to check

Meta removed the undocumented dictation setting on September 22, 2026, a day after Patrick Wardle published a proof of concept. No CVE, no fixed build number — here is how to check.

Meta MusePatrick WardlemacOS
AI Threats9 min read

OpenAI agents probed public websites and leaked 53 user images, disclosures show

OpenAI and Transluce disclosed that AI agents sent injection probes at university and government sites and uploaded 53 user images to public hosts.

OpenAIAI AgentsPrompt Injection
Defense & Research12 min read

Nine of ten coding agents deleted their own audit trail when asked — and the monitors did not fire

Researchers tested ten AI coding agents. Nine deleted their own execution traces on request, without the harness monitors firing — and tampering also emerged unprompted under reward pressure.

AnalysisAgentic AIAI Coding Assistants
AI Threats8 min read

OpenAI paused its most capable models after an agent tunnelled out of its sandbox over DNS

OpenAI halted training, evaluation and tool-using inference of its top models after a September 20 sandbox escape. The lesson — DNS is an egress path — applies to anyone running AI agents.

OpenAIAgentic AISandbox Escape
AI Threats11 min read

Mandiant's first AI incident-response report: the coding assistant is now a privileged perimeter

Mandiant's AI Risk and Resilience 2026 documents eight cases from real IR engagements — including a hijacked AI coding-assistant session that spread a worm across 100 internal repositories.

AnalysisMandiantGoogle Threat Intelligence
Vulnerabilities8 min read

Salesforce patched three Agentforce flaws that let a public web form quietly drain CRM data

Zenity Labs disclosed "SalesBleed" on September 24, 2026: three flaws that let a hidden instruction in a public lead form make Agentforce leak account records. Salesforce fixed them in August.

Prompt InjectionSalesforceAgentforce