Advisories
AI agent threats, explained clearly.
Real attacks against AI coding agents, MCP servers, and developer tools. Each advisory breaks down how the attack works, what to look for, and which Guard protections apply.
0
Supply-chain advisories
22
Curated patterns
6
Threat categories
14
Affected tools
Browse advisories
Click any advisory to see the full attack breakdown, detection steps, and Guard configuration.
No advisories match this filter.
Advisory questions, answered
An AI security advisory is a curated breakdown of a real attack pattern against AI coding agents and their tooling: how the attack works, what to look for, which Guard protections apply, and where other controls are still required.
The advisories cover attack patterns against AI coding agents, MCP servers, skills, plugins, and local command surfaces — including the harnesses HOL Guard supports, such as Codex, Claude Code, Cursor, and Gemini CLI.
Install HOL Guard to evaluate covered agent actions against your policy before they run, then follow each advisory's detection steps and Guard configuration guidance for the specific pattern.