prompt-injection
Safeguard articles tagged "prompt-injection" — guides, analysis, and best practices for software supply chain and application security.
127 articles
LLM Jailbreak as a Supply Chain Risk in 2026
A jailbreak in a model you ship downstream is a supply chain incident, not a trivia item. Here is how to reason about it and where the defensive controls belong.
Prompt Injection as a Supply Chain Risk in 2026
Prompt injection stopped being an LLM curiosity the moment agents started committing code. It is now a software supply chain risk and should be modeled as one.
AI Cybersecurity Glossary: Key Machine Learning & Security Terms
A defender's glossary of AI security terms — prompt injection, model poisoning, AI-BOM, adversarial ML — with dated, real-world incidents behind each one.
AI Agent Security: 6 Risks Beyond Traditional Controls
Gartner projects a third of enterprise apps will run agentic AI by 2028. Here are six AI agent security risks traditional controls miss.
Anthropic mcp-server-git: Three CVEs That Chain to RCE via Prompt Injection
Three flaws in Anthropic's official Git MCP server let prompt injection in a README compromise the developer's machine. The chain shows how MCP servers leak authority.
Artificial Intelligence and Cyber Security: Risks and Benefits
A balanced look at what artificial intelligence and cyber security actually means in practice today, the concrete benefits teams are seeing and the new risks AI introduces into the same systems.
Docker MCP Server: Setup and Security Considerations
Running a docker mcp server puts an AI agent's tool access inside a container boundary, which helps containment but doesn't remove the need to scope credentials and network access carefully.
MCP vs Skills vs Hooks vs Rules Explained
MCP, Skills, hooks, and rules extend AI coding agents in very different ways — two execute code, two only steer behavior. Here's how each one breaks.
ChatGPT Atlas and the Permanent Browser-Agent Injection Problem
OpenAI shipped ChatGPT Atlas in October 2025 and admitted by December that prompt injection in AI browsers may never be fully solved. Defenders need a posture, not a patch.
Security risks of multi-agent AI systems collaborating au...
Multi-agent AI systems introduce security risks classic AppSec misses: agent-to-agent exploits, swarm failures, and orchestration trust gaps.
Security implications of AI browser agents that click, br...
AI browser agents click, browse, and pay with your credentials -- and prompt injection attacks like EchoLeak and CometJacking prove they can be hijacked to do it.
Securing computer-use AI agents that operate desktops and...
Computer-use AI agents can click, type, and log into any app on your desktop. Here is how computer use AI agent security actually works in practice.