llm-security
Safeguard articles tagged "llm-security" — guides, analysis, and best practices for software supply chain and application security.
120 articles
Model Training Data and the Propagation of Insecure Codin...
LLM coding assistants inherit insecure patterns from their training data — from SQLi-prone snippets to hallucinated packages attackers exploit. Here's how the risk propagates.
How AI Code Generation Is Changing the Shape of the OWASP...
AI coding assistants are quietly reshuffling the OWASP Top Ten, elevating software supply chain risk and reviving old injection bugs at machine speed.
Common Insecure Suggestions in SQL and Auth Code from AI ...
Across studies from Stanford to BaxBench, AI assistants keep suggesting string-concatenated SQL and hardcoded JWT secrets. Here is the pattern, by the numbers.
Cisco's May 2026 Multi-Turn Jailbreak Study: Why Frontier Model Safety Collapses Over a Conversation
Cisco's AI threat team tested 15 flagship models with ~7,000 multi-turn attacks and found success rates as high as 88 percent. Single-turn safety scores told defenders almost nothing about real-world resilience.
Model Context Protocol Security 101: What Could Go Wrong ...
MCP lets AI models call tools automatically — and lets malicious servers hide instructions in plain sight. Here's how tool poisoning, rug pulls, and shadowing actually work.
Best AI red teaming tools ranked
Best AI red teaming tools ranked: how Mend.io's SCA scanning and Safeguard's exploitability-first SBOM analysis actually differ for AI supply chain risk.
Prompt Injection vs Traditional Injection Attacks: A Tech...
SQL injection was solved by separating code from data. Prompt injection can't be, because in an LLM they share one channel. Here's the technical comparison, with real exploits and dates.
The Jailbreaking Economy: How Model Vulnerabilities Get D...
Jailbreak prompts now trade like exploits: sold as $200/month "dark" chatbots, bountied by vendors for up to $15,000. Here's how that market actually works.
Distinguishing Model Risk from Application Risk in Agenti...
Model flaws and application flaws in AI agents cause different breaches and need different fixes. Real incidents show where each risk actually lives — and how to test for both.
Hacking AI: How Attackers Target Machine Learning Systems
Hacking AI is not science fiction; it is a growing set of concrete techniques that exploit how models learn, process input, and produce output. Here is how to think about defending against them.
What OpenAI and Anthropic Ecosystem Partnerships Signal A...
OpenAI and Anthropic's expanding ecosystem deals are an AI model vendor security partnership signal AppSec teams can no longer afford to ignore.
MCP Architecture Explained: A Security Guide
The Model Context Protocol connects AI models to tools and data through a client-server design. Understanding that architecture is the first step to securing it.
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.