Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

Behind the Binary by Google Cloud Security

Behind the Binary by Google Cloud Security artwork

EP22 Jailbreaking, Prompt Injection, and the "Agentic" Flaw in MCP with Kevin Harris

Feb 4, 202657 minAudio
ShareXLinkedInFacebookWhatsAppEmail

"Skilled adversaries have a 100% success rate against all of the defenses that we know about." In this episode, Kevin Harris defends that claim. We move past the standard "AI Safety" talking points to distinguish between the two attack vectors confusing the industry: Prompt Injection (an application-layer failure) vs. Jailbreaking ("gaslighting" the model via context shifting). Kevin argues that we haven't actually invented AI yet - we've just built a mirror that reflects our own intelligence (and psychosis) back at us. We also dissect the new model context protocol (MCP) and why giving "discretion" to agents that cannot think is potentially repeating the security mistakes of Web 2.0. THE SESSION: The "Pirate" Jailbreak: Why telling a model to be a pirate isn't just a party trick - it's a method of shifting the context window to bypass refusal patterns. The 100% Failure Rate: Why current defenses are only speed bumps for skilled adversaries, and why you are attacking the application, not the model. "There Is No AI": Kevin’s theory on why LLMs are just "predictive text made 3 orders of magnitude better" and the danger of "AI-induced psychosis". The Agentic Threat (MCP): A deep dive into the model context protocol. Why client-side authorization is the new "Browser Security" battleground, and why we are handing "table saws" to users who don't know how to use them. The Fix: Why "Attention Functions" are the key to understanding (and securing) the future of these models. Join the Community Research Hub: Threat research, training events and news: https://cloud.google.com/security/flare The FLARE Insider: Get community updates and announcements. To subscribe, email flare-external@google.com FOLLOW THE SHOW: Subscribe: Apple Podcasts | Spotify | YouTube

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. EP31 Syntactical Supremacy: Building and Breaking Obfuscating Compilers with Josh Stroschein

    Nov 18, 20261 hr 8 minAudio

    “We control the syntax. The semantics haven’t changed.” In Episode 31 of Behind the Binary, we switch seats. Co-host Blas Kajusner takes over the mic and turns the questions on regular host Josh Stroschein for a deep...

    Credit the people on this episode

  2. EP30 The Golden Age of macOS Malware: Evolution, Stealers, and AI Workflows with Christopher Lopez

    Oct 14, 202659 minAudio

    In this episode of Behind the Binary, we sit down with Mac security researcher Christopher Lopez (L0psec). to discuss the evolving landscape of macOS malware. As Mac adoption continues to grow in enterprise environments...

    Credit the people on this episode

  3. EP29 Binary Similarity in the LLM Era with Jonas Wagner and Endre Bangerter of ThreatRay

    Sep 16, 202657 minAudio

    "Throwing more LLM prompts at a packed binary won’t make your analysis faster. But combining code similarity with AI will." In Episode 29 of Behind the Binary, Jonas Wagner and Endre Bangerter of ThreatRay join the...

    Credit the people on this episode

  4. EP28 macOS Security Internals: Kernel Exploitation, PAC Defenses, and the Rise of macOS Infostealers with Olivia Gallucci

    Aug 26, 202652 minAudio

    In this episode, we're joined by security researcher Olivia Gallucci to explore macOS low-level security, kernel exploitation, and macOS threat trends. We break down how macOS internals differ from Linux - focusing on...

    Credit the people on this episode

  5. EP27 The Challenges of Reversing Modern Languages: From C++ to Go and Rust with Jae Young Kim

    Jul 15, 202656 minAudio

    When malware analysis first emerged, reverse engineers typically operated in a straightforward C landscape - standard Win32 APIs, no massive runtimes, and clear code paths. Today, the landscape has fundamentally...

    Credit the people on this episode