AI Security
In-depth guides and analysis on ai security from the Safeguard engineering team.
786 articles
AI Code Security Tools: risks of restricting them
Banning AI coding assistants doesn't remove the risk, it just removes visibility. Here's why restriction backfires and what actually secures AI-generated code.
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.
AI Chip Security: What Accelerators Mean for Your Threat Model
An AI chip is specialized hardware for running machine learning workloads, and it brings its own security concerns from supply chain to firmware. Here is what matters.
Software Supply Chain Attack News Today: What to Watch For
Software supply chain attack news today keeps pointing at the same target: open source package registries like npm and PyPI. Here is what the recent wave of attacks looks like and how to defend against it.
Gemini 2.5 Pro and the Late Safety Report
Google released Gemini 2.5 Pro Experimental on March 25, 2025 without a contemporaneous safety report. The UK reaction set a precedent.
Building Securely with AI (secure AI-assisted development)
AI coding assistants ship code fast — Veracode found 45% of AI-generated code contains security flaws. Here's what secure AI-assisted development actually requires.
Vector DB Security Considerations
Vector stores hold derivatives of your most sensitive text. We cover the access, isolation, and integrity controls production deployments of Pinecone and Weaviate need.
How Snyk Agent Fix's agentic retry loop self-corrects fai...
A technical look at how Snyk's Agent Fix uses a bounded, feedback-driven retry loop to validate and self-correct AI-generated vulnerability fixes before they reach a pull request.
AIBOM in 2026: Treating AI Models as a Software Supply Chain
The AI bill of materials is graduating from optional security artifact to procurement requirement. Here is what AIBOM/ML-BOM actually tracks in 2026, how it ties to the EU AI Act, and where it still falls short.
Slopsquatting: When AI Hallucinates Package Names
LLMs invent plausible package names; attackers register them and wait. How slopsquatting works, why hallucinations repeat predictably, and the gates that stop it.
OWASP Top 10 for LLM Applications explained
A breakdown of the 2025 OWASP Top 10 for LLM Applications—prompt injection, supply chain, excessive agency—with real examples and fixes.
Securing LangChain and LlamaIndex Applications in Production
Agent frameworks ship fast and patch fast. The CVE history, the dangerous defaults, and a production hardening baseline for LangChain and LlamaIndex apps.
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.