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.
Excessive agency turns a bad LLM output into an executed action. From Replit's July 2025 database deletion to Air Canada's chatbot ruling, here's what it is and how to scope it down.
Prompt injection is now OWASP's #1 LLM risk, and real incidents like EchoLeak and Slack AI prove it can mean zero-click data exfiltration. Here's how it works and what stops it.
A trojanized MCP server BCC'd every email it sent to an attacker for weeks, downloaded 1,643 times, before anyone noticed. Here's the pattern and the fix.
In August 2025, attackers hijacked Nx's npm publish token and used Claude Code, Gemini CLI, and Amazon Q as the exfiltration engine — leaking 2,349 secrets.
On March 19, 2026, TeamPCP hijacked Trivy's GitHub Action to steal LiteLLM's PyPI token, then shipped a backdoored release, CVE-2026-33634, CVSS 9.4.
A fake Solidity extension on Open VSX was downloaded 50,000+ times, dropped an infostealer, and drained $500K in crypto — how the marketplace trust model failed.
A 2025 USENIX study found LLMs hallucinate nonexistent packages in up to 21.7% of code samples — and attackers are already registering the names.
OWASP's LLM security list has grown from a 2023 side project into a 600+ expert initiative. Here's what each of the ten risks actually looks like in production.
Samsung engineers leaked chip source code into ChatGPT three times in 20 days. Here's how to build DLP controls that stop the next leak before it happens.
Weekly insights on software supply chain security, delivered to your inbox.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.
