ai-supply-chain
Safeguard articles tagged "ai-supply-chain" — guides, analysis, and best practices for software supply chain and application security.
19 articles
Protecting GenAI: OWASP Top 10 for LLMs
OWASP's Top 10 for LLM Applications reframes AI risk around prompt injection, data poisoning, and supply chain gaps that container-only tools like Aqua can't reach.
DeepSeek ClickHouse Exposure: When the AI Vendor Forgets the Database
In January 2025 Wiz Research found a wide-open ClickHouse instance belonging to AI startup DeepSeek, leaking chat history, API keys, and internal log streams. We unpack the AI-supply-chain implications.
AI Bill of Materials (ML-BOM) Standards in 2026
A senior engineer's survey of AI-BOM and ML-BOM standards in 2026, from CycloneDX ML components to SPDX 3.0 AI profile, and what to actually ship.
What is LLM Security
LLM security protects model weights, prompts, outputs, and the AI supply chain from injection, leakage, and compromise—here's what it covers and how to defend it.
Direct vs Indirect Prompt Injection
Direct and indirect prompt injection are different attack vectors with different blast radii. Real 2025 CVEs like EchoLeak show why the distinction matters.
NIST SSDF 1.2 Draft: What the Comment Period Revealed
NIST opened public comment on SP 800-218r1 SSDF v1.2 on December 17, 2025. The draft adds AI development practices, refines supply-chain controls, and aligns with EO 14306.
CycloneDX ML-BOM in 1.7: Implementation Guide
CycloneDX 1.7 was published in October 2025 and adopted by the General Assembly in December. We unpack what the ML-BOM capability means in practice for AI inventory.
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.