16 Nov 2026 The Apache Software Foundation with Ruth Suehle
Open source sustainability requires treating the ecosystem as a community rather than a supply chain, with foundations addressing governance and security challenges.
More Open Source Security episodes

Published 16 Mar 2026
Duration: 35:36
The text explores AI agent security risks like prompt injection and open-source vulnerabilities, emphasizing the No-NO project's kernel-based sandboxing with a deny-by-default model, hardware enclaves, and Rust-driven efficiency, alongside layered defenses, restricted commands, and collaborative efforts to tackle evolving threats like social engineering and insecure coding practices.
Josh talks to Luke Hinds, CEO of Always Further, about MCP and agent security. We start out talking about Luke's new tool, nono which is a sandboxing...
The text discusses the development of No-NO, a security tool created by Always Further, a startup focused on addressing vulnerabilities in AI agents and models. No-NO leverages kernel-based sandboxing to isolate processes, preventing data exfiltration, unauthorized file access, and destructive actions like rm -rf, using a deny-by-default model and hardware security enclaves (e.g., Apples Secure Enclave). Designed for speed and simplicity, it contrasts with Docker by enabling near-instant startup times and minimal user configuration, though it is not intended as a replacement but a complementary tool for specific use cases. The tool also incorporates restricted commands, time-based command allocation, and rollback mechanisms to mitigate risks like accidental deletions or unauthorized API interactions.
Broader challenges in AI security are highlighted, including the unpredictability of AI agents (e.g., bypassing sandboxing) and vulnerabilities in MCP servers (Model-Controller-Proxy), which enable AI models to execute external functions. Risks include supply chain vulnerabilities in open-source tools, prompt injection attacks, and the merged control/data architecture of large language models (LLMs), which make them susceptible to social engineering and data leaks. Historical parallels are drawn to early hacking exploits, such as the "2600 Hz" phone fraud, emphasizing the persistent difficulty of securing systems against autonomous, high-dimensional threats. The text also stresses the need for collaborative solutions, education in secure development practices, and tools that balance simplicity for non-experts with customization options for professionals, while addressing the growing gap between rapid AI innovation and robust security frameworks.
16 Nov 2026 The Apache Software Foundation with Ruth Suehle
Open source sustainability requires treating the ecosystem as a community rather than a supply chain, with foundations addressing governance and security challenges.
9 Nov 2026 Trusting your computing with Lance and Anton
Verifiable computing uses deterministic builds and hardware attestation to prove deployed software matches source code, mitigating supply chain attacks.
1 Nov 2026 Finding missing security backports with Roi Nisimi
AI enables mass discovery of unbackported open source vulnerabilities, outpacing under-resourced maintainers who struggle to fix them effectively.
5 Oct 2026 Dependency attacks in 2026 with James Matchett
"Software supply chain security faces evolving risks like install-time attacks, transitive dependencies, and AI-generated threats, requiring proactive monitoring, dependency firewalls, and regulatory compliance to balance security with developer flexibility."
21 Sept 2026 The curl summer of Bliss with Daniel and Stefan
"Explored open-source security challenges, highlighting curl's 'Summer of Bliss' initiative to reduce maintainer burnout, the impact of AI-generated vulnerability reports, and the need for human expertise in security management, while advocating for sustainable practices in open-source development."