AI Security insights
Securing AI features, LLM apps and AI agents.
LLM features and AI agents add a new attack surface: model inputs, retrieved documents and the tools an agent can call. These guides explain the attacks that matter, how to test for them and the design choices that limit the damage when a model misbehaves.
AI Security
AI Incident Response: How to Handle LLM Security Incidents
AI incident response for LLM features: spot leaks and prompt injection early, contain them with kill switches, keep the evidence and recover safely.
7 min read
AI Security
LLM Output Handling: How to Render AI Responses Safely
LLM output handling in practice: render responses as text, block markdown image leaks, validate structured output and keep it out of SQL and shells.
7 min read
AI Security
RAG Access Control: How to Stop Document Leaks
RAG access control in practice: enforce document permissions inside the search query, sync revocations, isolate tenants and test for leaks before launch.
7 min read
AI Security
PHP2Shell: How to Check and Patch Your PHP Servers
PHP2Shell (CVE-2026-109618, CVE-2026-109619) lets attackers run code on unpatched PHP. Find out if you're affected, how to patch, and what to check after.
7 min read
AI Security
How to Test an LLM Feature Before Launch
How to test an LLM feature before launch: what to attack, how to write test cases you can rerun, and the pass criteria to agree before go-live.
6 min read
AI Security
How to Secure AI Agents That Can Use Tools
AI agents that call tools can take real actions. How to scope their permissions, contain prompt injection and test an agent before it touches production.
6 min read
AI Security
Prompt Injection Explained for Product Teams
What prompt injection is, why it can't be solved with better prompts alone, and the design decisions that limit the damage in your AI features.
7 min read
Get AI security and automation insights, monthly
AI security, automation and governance, written by engineers. No spam, unsubscribe any time.