Safeguard
Tag

tool-poisoning

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

18 articles

AI Security

Security scanning for MCP servers and AI agent tool use

MCP servers give AI agents direct tool access, but most ship unvetted. Here's how security scanning catches tool poisoning and rug-pull attacks.

May 7, 20267 min read
Supply Chain Attacks

When the Vulnerability Is the Design: MCP STDIO Command Injection Across 150M Downloads (May 2026)

OX Security documented command injection through the MCP STDIO transport across Python, TypeScript, Java, and Rust SDKs. Anthropic calls the behavior by-design and won't patch upstream. That leaves the fix to thousands of downstream projects.

May 6, 202611 min read
AI Security

Line Jumping: How MCP Tool Descriptions Attack Before Tools Are Called

Trail of Bits coined 'line jumping' for prompt injection delivered through MCP tool descriptions on connection. It bypasses every tool-invocation guardrail by design.

Apr 21, 20266 min read
AI Security

Securing MCP Servers: A Practical Checklist

MCP servers are runtime dependencies your agent trusts implicitly. Here is a concrete checklist for auth, tool pinning, sandboxing, and monitoring before you ship one.

Mar 22, 20266 min read
AI Security

Claude MCP Tool Poisoning Threat Model 2026

A senior engineer's threat model for Claude MCP tool poisoning in 2026, covering malicious servers, description hijacking, and the authorization patterns that actually help.

Mar 21, 20267 min read
AI Security

MCP Server Capability Declaration Audit

An MCP server tells the world what it can do through its capability declaration. Auditing those declarations catches drift, tool poisoning, and misconfiguration before an agent gets talked into using the wrong one.

Jan 28, 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.

tool-poisoning (Page 2) — Safeguard Blog