The Hidden Security Risks of AI Coding Agents

The Hidden Security Risks of AI Coding Agents

Author: Tessl May 19, 2026 Duration: 41:45
Your AI coding agent has access to your secrets, pulls in content from the outside world, and can run shell commands. According to Joe Holdcroft, that combination makes you one prompt injection away from a very bad time. The tools haven't changed the fundamentals of security — they've just made every existing risk move faster, and introduced a few genuinely new ones. What we cover: Why the "lethal trifecta" of agent capabilities creates a novel threat surfaceHow text and markdown files have b...

Hosted by Guy Podjarny and Simon Maple, The AI Native Dev-from Copilot today to AI Native Software Development tomorrow is a conversation about the profound shift happening right now in how software is created. This isn't just another tech show about using the latest AI tool; it's a deep, ongoing exploration of what it means to build software in an age where artificial intelligence is a fundamental partner. Each episode unpacks the practical realities and the long-term implications of this transition, moving beyond today's assistive copilots to imagine the workflows, team structures, and architectural decisions of a fully AI-native future. For developers and engineering leaders who feel both the excitement and the uncertainty of this moment, the podcast offers grounded discussions, expert insights, and forward-thinking analysis. You'll hear concrete examples of AI's current impact on coding practices alongside speculative, thoughtful debates about where this all might lead. The dialogue is shaped by a genuine curiosity about how we can actively guide this transformation rather than just react to it. Tune in for a nuanced perspective that treats AI not as a simple productivity hack, but as the core of a new development paradigm that is still being written. This Tessl production provides a essential space for anyone invested in the craft of building software to understand and help shape what comes next.
Author: Language: en-us Episodes: 100

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow
Podcast Episodes
Why Tracking AI Usage Drives Better Results | Justin Reock & DX [not-audio_url] [/not-audio_url]

Duration: 51:43
With AI adoption surging across orgs, Justin Reock, CTO at DX, joins Simon Maple to break down the difference between meaningful integration and just chasing trends. They also get into: • two levers of velocity: quality…
Why AI Coding Agents Are Here To Stay | Patrick Debois [not-audio_url] [/not-audio_url]

Duration: 48:49
Patrick Debois, the mind behind “DevOps,” joins Simon Maple to unpack the system-level shifts AI is driving across software engineering, drawn from what he saw firsthand at the AI Engineer’s World Fair. They also get int…
The Graph Layer Behind NASA’s Breakthroughs | Michael Hunger [not-audio_url] [/not-audio_url]

Duration: 36:17
Michael Hunger of Neo4j, joins Simon Maple to unpack how graph databases inject structure, intent, and traceability into modern AI systems. On the docket: why relationships in data encode intentthe black-box problem in v…
The Missing Gap In Workflows For AI Devs | Baruch Sadogursky [not-audio_url] [/not-audio_url]

Duration: 48:52
Baruch Sadogursky, Head of Developer Relations at TuxCare, joins Simon Maple to explore why automated integrity needs to be built in before we rely on AI outputs. On the docket: the difference between specs and testswhy…
Why LLMs Keep Missing This One Thing | Jason Ganz [not-audio_url] [/not-audio_url]

Duration: 49:13
Can LLMs replace structured systems to scale enterprises? Jason Ganz, Senior Manager DX at dbt Labs, joins Simon Maple to unpack why, despite the rapid rise of AI systems, enterprises still rely on structured data for co…