ai-bom
Safeguard articles tagged "ai-bom" — guides, analysis, and best practices for software supply chain and application security.
38 articles
AI risk management best practices: a lifecycle framework
NIST's AI RMF has four functions and MITRE ATLAS now tracks 84 adversarial techniques — most AI risk programs still only cover one lifecycle stage.
The emerging role of the AI security engineer
OWASP's 2025 LLM Top 10 ranks prompt injection #1 and calls it structurally unfixable by parameterization — a signal that AppSec skills alone no longer cover the job.
What AI Executive Orders Actually Mean for Enterprise Security Teams
The US revoked its AI safety EO in January 2025, but SBOM and evidence obligations under EO 14028 never went away — and the EU AI Act just got harder deadlines.
OWASP Top 10 for LLM Applications: A Practical Walkthrough
OWASP's 2025 LLM Top 10 added three new categories in one revision — here's what changed, why, and concrete mitigation patterns for each risk.
A vendor-neutral checklist for rolling out AI coding assistants safely
437,000+ downloads of a vulnerable mcp-remote bridge and a backdoored Postmark MCP server prove AI assistants are now a live supply-chain surface, not a theoretical one.
AI Bill of Materials (AI-BOM) for Model Supply Chains
An AI-BOM tracks every model, dataset, and dependency in your ML pipeline so a compromised base model or license issue can be traced in minutes, not weeks.
How Snyk AI-BOM discovers agents, tools, models, and data...
How Snyk AI-BOM's static analysis engine discovers agents, tools, models, datasets, and MCP servers hiding in code, even without a manifest file.
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.
How Snyk AI-BOM generates a CycloneDX v1.6-compliant ML-BOM
How Snyk's aibom CLI uses static analysis to detect models, agents, and MCP servers, then maps them into a CycloneDX v1.6-compliant ML-BOM structure.
How Snyk AI-BOM's continuous refresh model differs from a...
How Snyk's AI-BOM keeps model and dataset inventories current through continuous refresh, and why that differs mechanically from a point-in-time static SBOM export.
How Snyk AI-BOM surfaces shadow AI usage that security te...
How Snyk's AI-BOM uses code-level analysis, not manifest parsing, to surface shadow AI models, agent frameworks, and MCP servers security teams don't know are running.
How Snyk's AI-BOM API lets teams query AI component inven...
How Snyk's AI-BOM API exposes AI model and dataset inventories as queryable, CycloneDX-aligned data teams can pull into CI, GRC, and asset tooling programmatically.
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.