Skip to content
AGT-07 governance

AI Agent Security

Prompt injection, MCP exfiltration, compromised agents. Red teaming, sandboxing, permissions, security hooks. What your CISO needs to know.

2 days (14 hours) CISO, CTO, DevSecOps, developers, security architects

What you'll be able to do

Identify attack vectors specific to AI agents

Conduct agent red teaming: injection, exfiltration, escalation

Configure defenses: hooks, MCP sandboxing, permissions

Build an AI governance policy

Align with NIS2, OWASP LLM Top 10, ISO 42001

Program

Day 1 — Morning

Threats and attack vectors

  • OWASP Top 10 for LLM Applications (v2.0, 2025): critical risks
  • Direct and indirect prompt injection: live demos
  • MCP supply chain: malicious servers, data exfiltration, poisoned dependencies
  • Shadow AI: unapproved agents in the company
Day 1 — Afternoon

Agent red teaming

  • Workshop: attacking an agent via web content injection
  • Workshop: exfiltrating data via a trapped MCP server
  • Workshop: escalating an agent's permissions
  • Analysis: which defenses held, which failed
Day 2 — Morning

Defenses and secure architecture

  • Security hooks: validate every action
  • MCP sandboxing: allowlists, denylists, per-tool permissions
  • Granular per-agent and per-context permissions
  • Real-time monitoring: detect anomalies
Day 2 — Afternoon

Governance and compliance

  • NIS2 and AI agents: obligations
  • AI security policy: template
  • Agent and MCP server validation process
  • Response plan: what to do when an agent goes rogue

Practical info

Duration

2 days (14 hours)

Target audience

CISO, CTO, DevSecOps, developers, security architects

Prerequisites

Cybersecurity basics. AI agent understanding (AGT-01 or AGT-02 recommended)

Group size

4 to 10 people

Pedagogy

30% theory, 70% offensive and defensive workshops on sandbox environments. Each participant leaves with an AI security policy.

Trainer

A Pyrmetia co-founder — AI developer and cybersecurity expert.

Pricing

Open enrollment
€950 / person / day
In-company
€5,500 / group (4-10 pers.) / 2 days

Post-training support

Security support for 30 days
Templates: AI security policy, checklist, response plan
Monthly AI threat watch
Follow-up session at D+15 (1 hour)

Request the full program

Bespoke program, tailored to your industry. First call is free.

Voir cette page en français