Safeguard
Tag

ai-security

Safeguard articles tagged "ai-security" — guides, analysis, and best practices for software supply chain and application security.

593 articles

AI Security

Supply Chain Attacks Targeting AI/ML Pipelines

AI and ML pipelines introduce unique supply chain risks -- from poisoned training data to compromised model registries. Here is what attackers are targeting and how to defend.

Jun 11, 20267 min read
Supply Chain

Nx s1ngularity: The First AI-Aware Supply Chain Worm

On August 26, 2025, malicious versions of Nx (20.9.0–21.8.0) harvested 2,349 credentials from 1,079 developers and weaponized Claude, Gemini, and Q CLIs to enumerate local secrets.

Jun 10, 20266 min read
AI Security

Open-Weight Model Sandboxing Patterns

Running an open-weight model inside an enterprise perimeter seems safer than calling a hosted API. It is, and it isn't. The sandboxing patterns that actually produce the safety properties.

Jun 10, 20266 min read
AI Security

Security in AI Systems: What Actually Changes

Security in AI systems isn't a wholly new discipline, but prompt injection, training data provenance, and model supply chains introduce risks traditional AppSec tooling wasn't built to catch.

Jun 10, 20265 min read
AI Security

Introducing Agentic Development Security (ADS)

As AI agents now author up to half of production commits, Safeguard introduces Agentic Development Security (ADS) — a new framework for securing autonomous coding.

Jun 10, 20267 min read
AI Security

GPT-5 Launch: Reading the System Card for Supply-Chain Risk

GPT-5 shipped August 13, 2025 under OpenAI's Preparedness Framework v2. Here's what the system card tells security teams about deployment risk.

Jun 8, 20266 min read
AI Security

Data poisoning attacks against LLMs

A $60 domain purchase or 250 documents can backdoor an LLM. Here's how data poisoning attacks work, real cases, and how to defend against them.

Jun 8, 20267 min read
AI Security

Securing RAG pipelines against injection attacks

RAG pipelines feed untrusted retrieved content straight into model context. Real breaches like EchoLeak show what happens when nothing checks it.

Jun 8, 20267 min read
AI Security

Type-level security: the future of secure AI code generation

45% of AI-generated code fails basic security tests. Here's why type systems catch what code review misses, and how to enforce type-level security on AI-authored diffs.

Jun 8, 20268 min read
Industry Analysis

How Snyk AI-BOM detects MCP servers connected to an appli...

A technical look at how Snyk's AI-BOM statically detects MCP client-server connections in source code, what CycloneDX data it captures, and where its coverage stops.

Jun 7, 20268 min read
Vulnerability Analysis

NVD in the AI era: multi-source vulnerability intelligence

NVD's 2024 enrichment backlog exposed the risk of a single vulnerability feed. Here's how multi-source data and AI triage close the gap.

Jun 7, 20266 min read
AI Security

Snyk VulnBench: benchmarking LLMs on repeat vulnerability discovery

Snyk's VulnBench JS 1.0 ran 300 repeated LLM scans and found half of non-reference findings vanish on rerun—raising the bar for AI security tooling.

Jun 7, 20267 min read

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.

ai-security (Page 17) — Safeguard Blog