AI SECURITY
23 items
23 posts
Blog
Prompt Injection in Agent Apps: The Practical VersionPrompt injection stops being an abstract LLM risk once an agent can call tools. The practical defense is data boundaries, structured handoffs, tool guardrails, and approval gates around side effects.
Blog
AI Security Scanners Move the Bottleneck to TriageAnthropic's Project Glasswing update is a useful signal for developer teams: AI can find vulnerability candidates faster than humans can verify, disclose, patch, and ship them.
Blog
Open Source Has a Bot Problem: Prompt Injection in Contributing.mdAI coding agents now read repository docs, config, issues, and comments before opening pull requests. That turns CONTRIBUTING.md and AGENTS.md into part of the security boundary.
PreviousPage 2 of 2
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever