Safeguard
Topic

AI Security

In-depth guides and analysis on ai security from the Safeguard engineering team.

676 articles

AI Security

Least Privilege for AI Agents: Why It's Harder Than It So...

AI agents break least-privilege assumptions built for humans: they chain tools, act autonomously, and compose narrow scopes into broad access no one reviewed.

Jul 21, 20257 min read
AI Security

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.

Jul 21, 20257 min read
AI Security

How Malicious Payloads Get Smuggled Into Trusted AI Skill...

Attackers smuggle malicious payloads into trusted AI skill repositories via typosquats, staged fetches, and split-file obfuscation — here is exactly how it works.

Jul 20, 20258 min read
AI Security

What an AI Model Risk Registry Should Actually Track

Most AI model inventories are name-and-owner spreadsheets. Here's the provenance, licensing, CVE, and revalidation fields a real AI model risk registry needs to track.

Jul 20, 20257 min read
AI Security

Agentic AI Security Glossary: Tool Poisoning, Prompt Inje...

A precise glossary of agentic AI security terms — prompt injection, tool poisoning, model jailbreaking, excessive agency, and MCP rug pulls — with concrete attack examples.

Jul 20, 20258 min read
AI Security

MCP Server Permissions: A Practical Checklist for Reducin...

A practical checklist for scoping MCP server permissions, denying risky defaults, and limiting the blast radius when an AI agent's tool access is exploited.

Jul 20, 20258 min read
AI Security

Why Traditional SAST Tools Struggle to Analyze Agentic Co...

Agentic codebases build call graphs at runtime, defeating static analysis. Here's why SAST tools miss prompt injection and tool-schema risks—and how Safeguard closes the gap.

Jul 19, 20257 min read
AI Security

Venture Capital's Renewed Bet on Agentic AI Security Star...

VC funding for agentic AI security startups hit new highs in 2026, with identity governance, autonomous pentesting, and SOC automation drawing the biggest rounds.

Jul 14, 20259 min read
AI Security

MCP 2025-06-18: OAuth Resource Server Rules Defenders Must Understand

The June 2025 MCP spec made every server an OAuth 2.1 resource server, mandated RFC 8707 resource indicators, and added elicitation. Here is what changes for blue teams.

Jul 9, 20256 min read
AI Security

Asana MCP Cross-Tenant Leak: A SaaS Connector Failure Mode

From May 1 to June 17, 2025, Asana's MCP server exposed records from one customer's workspace to another. The bug was a textbook authorization break wearing an AI label.

Jul 2, 20257 min read
AI Security

EchoLeak (CVE-2025-32711): The First Zero-Click LLM Exfiltration in Production

Aim Security's CVE-2025-32711 exfiltrated Microsoft 365 Copilot data via a single crafted email. The XPIA classifier failed, CSP let attackers through, and CVSS 9.3 followed.

Jun 24, 20256 min read
AI Security

EchoLeak (CVE-2025-32711): The First Zero-Click Production LLM Exfiltration

A single crafted email could exfiltrate data from Microsoft 365 Copilot without a user click. We walk the attack chain, the patch, and the lessons for agent operators.

Jun 19, 20256 min read
AI Security (Page 54) — Supply Chain Security Blog | Safeguard