llm-security
Safeguard articles tagged "llm-security" — guides, analysis, and best practices for software supply chain and application security.
120 articles
The blind spots of single-model AI security tooling
OpenAI's API went down three separate times in 2024 alone — if your SAST pipeline hard-depends on one model provider, its outages and blind spots become yours.
A Checklist for Reviewing AI-Generated Code Before It Merges
19.7% of packages LLMs recommend don't exist in real registries, per a 576,000-sample USENIX 2025 study — here's what to check before merging AI-written code.
Can an LLM find the same bug twice? What repeatability benchmarking reveals
In a 300-run benchmark, the best LLM scanner hit 75.4% F1 while a deterministic SAST baseline hit 100% — but the real story is in what varies between runs.
Best AI Code Security Tools in 2026: An Honest Buyer's Guide
A balanced 2026 comparison of tools for securing AI-generated code and AI-native applications — Semgrep, CodeQL with Copilot Autofix, Snyk, Socket, Endor Labs, and model-layer tools — with an honest look at where Safeguard fits.
The LLM Application Security Checklist (2026)
You are shipping an LLM feature. Before it goes live, walk this checklist — organized around the OWASP Top 10 for LLM Applications — to catch the risks that matter most in production.
LLM Jailbreak Prevention: A Defense-in-Depth Playbook
A jailbreak is not the same thing as a prompt injection, and conflating them leads to defenses that miss. Here is how modern jailbreaks actually work and the layered controls that hold the line.
Prompt Injection Prevention: A Defense-in-Depth Guide
Prompt injection is the top risk on the OWASP list for LLM applications for a reason: there is no single patch. Preventing it means layering controls around a model that cannot reliably tell instructions from data.
AI Security Software: A Buyer's Guide for 2026
The label 'AI security software' now covers two different markets — tools that secure AI systems, and security tools powered by AI. How to tell them apart, what to evaluate, and the questions that expose thin products.
RAG Security Best Practices for 2026
Retrieval-augmented generation wired an untrusted-content pipeline straight into your model's context window. Here are the practices that keep a poisoned document or a leaked chunk from becoming an incident.
Reducing false positives in secret scanning with context-...
Regex-based secret scanners like GitHub Advanced Security flood teams with false positives. Here's how context-aware LLM reasoning cuts the noise without missing real leaked credentials.
Prompt Injection Examples: Attacks Seen in the Wild
From hidden text in resumes to poisoned web pages that hijack AI browsing agents, prompt injection has moved from research demos to real incidents. Here are the patterns and what actually blunts them.
AI Agent Memory: Security Risks
Persistent memory makes AI agents more useful and more dangerous. A security engineer's walkthrough of how agent memory gets poisoned, exfiltrated, and weaponised, with concrete 2025 examples.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.