Safeguard
Tag

agent-security

Safeguard articles tagged "agent-security" — guides, analysis, and best practices for software supply chain and application security.

36 articles

Agent Security

MCP Spec 2025-11-25: Tasks, URL Mode Elicitation, and What Defenders Must Watch

The November 25, 2025 Model Context Protocol release adds Tasks, formalises long-running work, and reshapes the audit story for enterprise MCP.

Jul 28, 20266 min read
AI Security

Securing MCP Servers for AI Agents

Five CVEs in 2025 alone trace MCP tool compromise back to one root cause: unsanitized strings piped into exec(). Here's how to expose and consume MCP safely.

Jul 9, 20267 min read
AI Security

Signing and provenance standards for AI agent skill registries

Shai-Hulud infected 500+ npm packages via stolen tokens in 2025. Agent skill registries are repeating the same unsigned-artifact mistake — here's the fix.

Jul 9, 20267 min read
Supply Chain Attacks

How Malicious Skills Get Distributed Through Agent Registries

CVE-2025-59536 (CVSS 8.7) let a single malicious commit auto-approve MCP servers in Claude Code, no install click required. Registries need the same controls as package managers.

Jul 8, 20266 min read
AI Security

Prompt injection in AI coding assistant system prompts

Copilot, Cursor, and Windsurf all read untrusted repo text into the same channel as trusted instructions — three 2025 CVEs show what happens next.

Jul 8, 20266 min read
AI Security

Vetting third-party agent skills before you install them

AI agent skill marketplaces run installed code with your full permissions and no sandboxing — VS Code's 2025 extension attacks show exactly how that gets abused.

Jul 8, 20266 min read
FAQ

Agentic AI Security FAQ: Governing Autonomous AI in 2026

Clear answers on securing agentic AI — what makes autonomy risky, how tool scope and identity work, prompt injection and confused-deputy failures, and how Safeguard governs agents that act on your systems.

Jul 6, 20266 min read
FAQ

MCP Server Security FAQ: Safeguarding AI Agent Tool Access in 2026

Plain answers about securing the Model Context Protocol — what an MCP server exposes, how agents authenticate, the prompt-injection and tool-poisoning risks, and how Safeguard's MCP server fits in.

Jul 4, 20266 min read
Agent Security

The MCP Registry and the Namespace-Impersonation Problem

The official MCP Registry launched in September 2025 with namespace-bound publishing. We unpack the trust model and what it does — and does not — defend against.

Jul 4, 20266 min read
AI Security

What Is a Claude Code Skill, and How Do You Secure One?

A Claude Code skill is a folder of Markdown instructions and scripts that an AI agent loads on demand. Because it can carry executable code, it deserves the same review as any dependency.

Jun 24, 20267 min read
Agent Security

Devin's Sandbox: What the Autonomous Engineer Threat Model Looks Like

Cognition's Devin executes engineering tasks autonomously in cloud sandboxes. We unpack the trust boundaries, the human checkpoints, and what defenders must require.

Jun 3, 20267 min read
Agent Security

Supabase MCP and the Lethal Trifecta: When an Agent Has service_role

A Cursor user's Supabase MCP server was tricked by a support ticket into exfiltrating an integration_tokens table. The bug was not in MCP. It was in the trifecta.

May 25, 20267 min read

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.

agent-security — Safeguard Blog