AI Security
Memory and Context Poisoning Attacks Against AI Agents
How attackers poisoned ChatGPT's memory and RAG pipelines to hijack AI agents long-term, and the controls Safeguard uses to catch it before it spreads.
Jul 21, 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
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.
Jul 21, 20268 min read
AI Security
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.
Jul 20, 20267 min read
AI Security
Agentic Identity and Privilege Abuse
AI agents now inherit more privilege than they need — and incidents like the Microsoft 38TB SAS-token leak and ServiceNow's Now Assist flaw show what happens when that privilege gets abused.
Jul 20, 20268 min read
AI Security
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.
Jul 20, 20268 min read
AI Security
Agent Goal Hijacking: Redirecting Autonomous AI Objectives
Attackers are hijacking autonomous AI agents by planting instructions in content they read—no exploit needed. Here's how it works, real 2025 incidents, and defenses.
Jul 20, 20268 min read
AI Security
LLM Misinformation: Security Risks of Hallucinated Outputs
LLM hallucinations aren't just AI trivia — they invent packages attackers squat on, fake CVEs, and false advisories that have already cost real companies real money.
Jul 20, 20268 min read
AI Security
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.
Jul 19, 20269 min read
AI Security
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.
Jul 19, 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.