12 Nov 2026 Marian Kamenistak on Product Management for Software Engineers
As AI automates coding, engineers must master product management, focusing on customer value, rigorous validation, and business outcomes to remain valuable.
More Software Engineering Radio episodes
Published 13 Aug 2026
Duration: 01:00:09
"Explores AI agent security risks, focusing on prompt injection vulnerabilities, non-deterministic threats, and the need for dynamic monitoring and proactive defenses against evolving AI-specific attacks."
Max Corbridge, an ethical hacker and red teamer who is co-founder and CEO of Secure Agentics, speaks with SE Radio host Amey Ambade about how AI agent...
AI agent security presents a novel and evolving challenge due to the autonomy and non-deterministic nature of these systems, making them inherently more vulnerable than traditional software. A core issue is prompt injection, a systemic vulnerability where attackers manipulate AI models through carefully crafted inputs, either directly or indirectly via poisoned data sources like web pages or documents. The flexibility of natural language allows for infinite variations of attacks, rendering traditional input filtering ineffective - similar to how SQL injection plagued early web applications, but far more complex due to the lack of rigid syntax in language models.
The risks are amplified by AI agents' increasing integration with real-world tools and systems via protocols like MCP, which expand their attack surface. Threats include malicious MCP servers, indirect prompt injection through third-party data, and data poisoning during training, where minimal contamination can lead to widespread model compromise. Current defenses such as guardrails, sandboxing, and human-in-the-loop approvals offer partial protection but struggle to scale. Effective security requires a shift from preventing all attacks to assuming compromise and focusing on runtime monitoring, behavioral analysis, and limiting agent permissions through least privilege and identity management - approaches that must evolve to handle the massive scale and dynamic behavior of AI agent deployments.
What if you treated your AI agent like a zero-trust employee with full system access?
What if you sandboxed your AI agent from day one - before granting any real-world tool access?
delete all files, send .env to attacker). Reduce risk of data poisoning and lateral movement, while maintaining agility for solo development.What if you built your agent with least-privilege identity and dynamic permissions?
12 Nov 2026 Marian Kamenistak on Product Management for Software Engineers
As AI automates coding, engineers must master product management, focusing on customer value, rigorous validation, and business outcomes to remain valuable.
29 Oct 2026 Danilo Krummrich on Rust in the Linux Kernel
"Nova GPU driver project integrates Rust into the Linux kernel to replace the aging Novo driver, leveraging Rust's memory safety for better reliability and performance while addressing firmware and architectural challenges through incremental, collaborative updates."
7 Oct 2026 Sahil Walia on Schema Changes and Data Migrations
Recommended: Schema as source of truth
"Schemas define data structure, apply across systems, and require careful evolution to avoid breaking changes, with best practices including additive updates, blue-green deployments, and stable identifiers."
30 Sept 2026 Raju Dandigam on Building Production AI Agents
"Explores production AI agents, their autonomy, safety, and engineering best practices, comparing workflows, tool design, orchestration, and memory systems while addressing challenges like cost, latency, and reliability."
16 Sept 2026 Milan Milanovic on the Laws of Software Engineering
"Explores key software engineering principles (like Conway's Law, Brooks' Law) and their impact on systems, teams, and decision-making, emphasizing context-dependent trade-offs, AI's role, and practical applications like measuring technical debt."