Guardians of Agents

A weekly briefing on agentic AI security

AI agents now act on our behalf. Here is how they fail, and how to keep them in check.

Guardians of Agents publishes a free, weekly briefing on agentic AI security: why agents are dangerous, real incidents and their aftermath, kill switches and guardrails, red teaming, the industry and research landscape, and where it is all heading.

Latest issue

Issue 09 · Control & Guardrails

Identity for AI Agents: Who Is Acting, and on Whose Authority?

Agents act for people, for themselves and for other agents, often with long-lived keys. How delegation, MCP authorization, agent identities and short-lived credentials keep an agent from becoming a confused deputy.

· 11 min read

  1. Nov 23Agents Talking to Agents: Securing MCP, A2A and Multi-Agent SystemsControl & Guardrails
  2. Nov 30How to Red Team an AI Agent: Goals, Harnesses, Benchmarks, MetricsRed Teaming Agents
  3. Dec 7Who Writes the Rules for AI Agents? Standards, Labs and GovernmentsIndustry & Players

Earlier issues

All articles

Issue 08 · Control & Guardrails

Agent Guardrails: What Each Layer Catches, and What Gets Through

Classifiers, monitors, policy engines, human approval and secure-by-design patterns each stop some agent failures. Here is what the measurements say about each one, how attackers get past them, and how to layer them.

· 11 min read

Issue 07 · Control & Guardrails

The Agent Kill Switch: Building a Stop Button That Works

Laws now ask for a stop button, but an agent is a loop plus credentials, sandboxes and side effects. Here is a layered kill-switch architecture, what vendors ship, and where stopping fails.

· 14 min read

Issue 06 · Incidents & Aftermath

When Agents Act on Their Own: Scheming, Sabotage and Shutdown

Lab tests show models editing shutdown scripts, blackmailing and gaming their graders. Here is what the primary research found, what it did not find, and how to design agents that stay safe either way.

· 14 min read

Issue 05 · Incidents & Aftermath

The Aftermath: What Two Years of Agent Incidents Changed

Agent incidents forced patches, new bounty rules, CVEs for prompt injection, a court ruling, insurance exclusions and browser bans. Here is what changed, what held, and the patterns behind fifteen cases.

· 15 min read

Issue 03 · Incidents & Aftermath

When Coding Agents Go Wrong: The 2025-2026 Incident File

From Replit's deleted database to a GitHub issue title that poisoned Cline's releases: a worldwide file of coding-agent incidents, what caused each one, and what changed afterward.

· 14 min read

Research atlas

Open the atlas

A classified map of 1,472 papers on attacking, defending and controlling AI agents: method families, maturity, results under adaptive attack, and open problems. Searchable, with a downloadable dataset.

Industry map

Open the map

170 companies, platforms, labs and open-source projects securing AI agents, sorted by method, maturity and funding, with every acquisition since 2024 and a searchable table.

The curriculum