💉 Prompt Injection - emschwartz

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

🤝Multi-Agent Orchestration Code

github.com··Hacker News

ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

🛡️AI Security

the-decoder.com

OpenAI rolls out Lockdown Mode to more ChatGPT users to fight prompt injection attacks

🛡️AI Security

alternativeto.net·

From prompt to pwned: chaining LLM and web bugs to Admin

🛡️AI Security Blog

blog.quarkslab.com·

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

🛡️AI Security Academic

arxiv.org·

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

🕳LLM Vulnerabilities Discussion

langprotect.com··DEV

Gemini Voice Assistant Hijacked via Messaging Notifications

🕳LLM Vulnerabilities

securityweek.com·

How I Gave My Security Blog Its Own AI Agent and an Attitude

🛡️AI Security Blog

medium.com

The AI automation tool nobody talks about just replaced my entire workflow setup

🛡️AI Security

xda-developers.com·

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

🛡️AI Security

techcrunch.com··Hacker News

OpenAI Unveils ChatGPT Account Security Controls

🛡️AI Security News

infosecurity-magazine.com·

Tiberius: A Security Testing Framework for LLM Applications in Java

🕳LLM Vulnerabilities

foojay.io·

agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.

📋MCP Code

github.com··Hacker News

OpenAI Help: Lockdown Mode

🛡️AI Security

simonwillison.net·

Less-relevant results

What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator

🛡️AI Security

techcommunity.microsoft.com·

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

🛡️AI Security Academic

arxiv.org·

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

🕳LLM Vulnerabilities Blog

varonis.com··Hacker News

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

🛡️AI Security

thehackernews.com·

Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks

Prompt Injection in RAG Agentic Systems

ashp15205/guardian-runtime: A zero-latency, local-first runtime firewall for LLMs. Intercept every prompt and response locally to stop data leaks and runaway token costs.

ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

OpenAI rolls out Lockdown Mode to more ChatGPT users to fight prompt injection attacks

From prompt to pwned: chaining LLM and web bugs to Admin

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

Gemini Voice Assistant Hijacked via Messaging Notifications

How I Gave My Security Blog Its Own AI Agent and an Attitude

The AI automation tool nobody talks about just replaced my entire workflow setup

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

OpenAI Unveils ChatGPT Account Security Controls

Tiberius: A Security Testing Framework for LLM Applications in Java

agentsploit/agentsploit: Offensive security framework for AI agents and MCP servers.

OpenAI Help: Lockdown Mode

What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

Phishing for Lobsters: How We Tricked OpenClaw into Spilling Secrets

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration