AI Security
LLM Insecure Plugin Design Vulnerabilities
ChatGPT plugins, LangChain agents, and MCP servers have all shipped insecure plugin flaws exposing accounts and data. Here's how Safeguard defends against them.
Jul 17, 20268 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
LLM Denial of Service Attack Techniques
LLM denial of service attacks exploit sponge prompts, unbounded generation, and denial-of-wallet loops to cripple AI systems without a single exploit.
Jul 17, 20267 min read
AI Security
Excessive Agency in LLM-Powered Applications
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.
Jul 16, 20268 min read
AI Security
Prompt Injection Attack Techniques and Defenses
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.
Jul 16, 20267 min read
AI Security
The Cursor extension that cost a developer $500,000
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.
Jul 16, 20266 min read
AI Security
When the Scanner Is the Backdoor: The LiteLLM Trivy Attack
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.
Jul 16, 20266 min read
AI Security
The Nx Attack Turned AI Coding Agents Into the Malware
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.
Jul 16, 20266 min read
AI Security
The postmark-mcp Backdoor: What MCP Server Vetting Should Look Like
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.
Jul 16, 20267 min read
AI Security
Can AI-Generated Code Be Trusted? A Security Review
A 2025 USENIX study found LLMs hallucinate nonexistent packages in up to 21.7% of code samples — and attackers are already registering the names.
Jul 13, 20267 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.