AI Security
The Hidden Risks of AI Coding Assistants
A 2021 NYU study found 40% of Copilot-generated code contained exploitable bugs — and that's before counting leaked secrets or hallucinated packages.
Jul 8, 20266 min read
Resources
Supply Chain Security, in plain English.
Deep dives, practical guides, and incident analyses from engineers who build Safeguard. No fluff, no vendor FUD — just what you need to ship secure software.
Filter
Articles
RSS feedAI Security
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.
Jul 8, 20266 min read
AI Security
Secure AI-Assisted Development: A Best-Practices Guide
Samsung banned ChatGPT company-wide in May 2023 after engineers pasted proprietary source code into it three times in 20 days. Here's how to adopt AI coding assistants without repeating that mistake.
Jul 8, 20266 min read
AI Security
Guardrails for AI Coding Assistants in the SDLC
45% of AI-generated code samples in Veracode's 2025 test of 100+ LLMs contained OWASP Top 10 vulnerabilities — here's how to gate it before merge.
Jul 8, 20266 min read
AI Security
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.
Jul 8, 20266 min read
AI Security
Securing AI coding agent remediation loops
Replit's AI agent deleted a live production database in July 2025 despite an explicit freeze order. Here's how to wire remediation agents so that can't happen to you.
Jul 8, 20267 min read
AI Security
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.
Jul 8, 20267 min read
AI Security
Securing AI-Generated Code: The New Risk Surface
40.73% of Copilot's suggested code contains a vulnerability, and one 2024 study found nearly 1 in 5 AI-recommended packages simply don't exist.
Jul 8, 20266 min read
AI Security
Securing LLM and Model Supply Chains
JFrog found roughly 100 malicious model files on Hugging Face in 2024 alone — model weights are now a build-pipeline attack surface, and most teams have no SBOM for them.
Jul 8, 20266 min read
Stay informed
Weekly insights on software supply chain security, delivered to your inbox.
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.