Security: AI Agents That Audit Your Own Stack
Point an agent arsenal at your own site — then verify what it actually found.
An hour of live, authorised security work. Install the T3MP3ST framework from Claude Code, open its War Room, and approve a target you own before anything runs. The agents coordinate as subagents, pull from a Kali-style arsenal, and return a genuine assessment citing real CVEs — and it found actual vulnerabilities in a production site built with Claude Code. The second half is the part most demos skip: verifying the findings by reading the code instead of trusting the agent, judging whether a downloaded security toolkit has a backdoor of its own, and seeing how prompt injection and jailbreaks work well enough to defend against them.
$20.00 USD
What you will learn
- Install and run the T3MP3ST security framework from inside Claude Code
- Gate every run behind an explicit target approval — and why testing what you do not own gets you sued
- Coordinate subagents against a Kali-style arsenal instead of running tools by hand
- Read an assessment that cites real CVEs, then verify each finding against the source
- Judge whether a downloaded security toolkit is safe to run at all
- Understand prompt injection and model jailbreaks well enough to defend your own agents
What is included
- Full recording of the live session (MP4, download and keep)
- Complete written transcript
- Private download link, delivered automatically after payment
Other masterclasses
Prefer live, personalised sessions? The 1:1 programme covers all of this and builds your own system over 20 hours.