supply-chain-security
Safeguard articles tagged "supply-chain-security" — guides, analysis, and best practices for software supply chain and application security.
1106 articles
Agentic Unexpected Code Execution Vulnerabilities
How AI agents with code-execution tools get hijacked by prompt injection—from the Vanna.ai RCE (CVE-2024-5565) to LangChain and MCP—and what to do about it.
Outdated container images still running in production
New industry data shows most production containers still run on stale, vulnerable base images months after fixes ship -- here's why, and how to close the gap.
Agentic AI Supply Chain Vulnerabilities
Agentic AI systems trust tools and models at runtime, not build time. Real 2024-2025 incidents show how MCP servers and AI packages become supply chain attack vectors.
Container registry credential leak trends
2026 data shows container registry credential leaks accelerating as CI pipelines speed up — and why layer-aware scanning, not just final-image checks, is now essential.
Agent Tool Misuse and Exploitation
Attackers don't need to hack AI agents — they just redirect their own tools. Here's how tool misuse works, real 2025 incidents, and how to stop it.
Kubernetes Helm chart vulnerability trends
New Safeguard research finds most public Helm charts ship risky defaults and stale image pins—here's what the data shows and how to fix it.
.NET deserialization vulnerability landscape
A look at the .NET deserialization vulnerability landscape — from the 2025 ASP.NET machine key crisis to BinaryFormatter's retirement and Telerik exploits.
LLM Unbounded Consumption: Resource Exhaustion Attacks
How attackers exploit token-based pricing and growing context windows to exhaust LLM compute and inflate cloud bills — and the concrete limits that stop them.
LLM Vector and Embedding Weaknesses
Embeddings aren't anonymized math — Vec2Text recovers 92% of text from vectors, and OWASP's LLM08:2025 now names inversion, poisoning, and exposed vector DBs as core AI risks.
Best CI/CD pipeline security tools
A fair, no-hype buyer's guide to CI/CD pipeline security tools: what to evaluate, six real vendors compared, and where Safeguard fits in the stack.
Model Theft: Protecting Proprietary LLMs from Extraction ...
A $20 API attack can clone a production LLM's embeddings. Here's how model extraction works, real incidents from LLaMA to DeepSeek, and how to protect proprietary models.
Training Data Poisoning Attacks on Machine Learning Models
A $60 domain purchase or 0.001% of training tokens can silently corrupt an ML model. Here's how training data poisoning attacks work and how to defend against them.
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.