
Is It the Model or the Harness? | Episode 54
From AI Security Ops by Black Hills Information Security
June 1, 2026 · 20 min · Episode 54
About this episode
The episode discusses the shift in AI security focus from the model to the harness surrounding it.
In this episode of BHIS Presents: AI Security Ops, the team tackles a foundational question in modern AI security: Is the real risk in the model… or in the harness around it? For years, most conversations have focused on model behavior — prompt injection, refusals, alignment, and safety controls. But as AI systems evolve into full agents with tools, memory, and execution capabilities, the focus is shifting. Increasingly, the real security boundary isn’t the model itself — it’s the harness: the code, integrations, permissions, and workflows that give AI systems real-world power. And that shift has massive implications for how we think about AI risk. We dig into: • What “model vs. harness” actually means in practical terms • Why defenders often blame the model for issues caused by the harness • How agent architectures expand the attack surface beyond prompts • The role of tools, memory, and execution in modern AI systems • Why prompt injection is often a harness design failure • How real-world AI exploits increasingly target integrations, not models • The limits of model-level safety and refusal behavior • Why harness design is becoming the new security perimeter • How AI agents…
People in this episode
Host: Black Hills Information Security
Topics covered
- AI security
- model vs harness
- prompt injection
- agent architectures
- real-world AI exploits
- harness design
Keywords
- AI risk
- model behavior
- safety controls
- attack surface
- integrations
- permissions
- workflows
Mentioned in this episode
Organizations: AI Security Ops
More episodes of AI Security Ops
- AI Cost Saving Tips | Episode 55 · June 4, 2026 · 30 min
- AI News | Episode 53 · May 22, 2026 · 29 min
- Agent Pentest Benchmarking | Episode 52 · May 14, 2026 · 18 min
- AI and Bug Bounties | Episode 51 · May 11, 2026 · 14 min
- Vercel Breach | Episode 50 · May 1, 2026 · 18 min
- Claude Mythos | Episode 49 · April 24, 2026 · 26 min
Explore listener stats, chart rankings, contacts and more on the AI Security Ops podcast page.