Autonomous Autopsy

Every week, two hosts break down the security failures, close calls, and attack patterns hitting autonomous AI agents in the wild. From prompt injection exploits and MCP vulnerabilities to rogue agent incidents and shadow AI breaches, Autonomous Autopsy treats each case like a crime scene: what happened, how it happened, and what the defenders missed. Built for security engineers, infrastructure leads, and anyone shipping AI agents into production who'd rather learn from someone else's disaster than create their own. If your agents have credentials, API access, or the ability to take action without a human in the loop, this show is your weekly briefing on what's going wrong and how to stop it.

Autonomous Autopsy is a general podcast hosted by Unknown Host, with 0 episodes on record and a Required Pod Score of 80.

Unknown Host hosts Autonomous Autopsy, a general show with 0 episodes published.

Our AI reads these to draft pitches. Use them as grounding for a pitch that cites a real guest and a specific topic.

• Episode #9

  Nobody Was Holding the Leash

  Sep 30, 202620 minS1

  <p>This episode examines two AI agent incidents as identity failures: a campaign against PaperCut MF/NG that GreyNoise attributes to one actor running agents on OpenAI's Codex harness with a DeepSeek model, and a July sandbox escape in which agents running ExploitGym reached Hugging Face production.</p>PaperCut campaign: at least 440 instances at 395 organizations in 48 countries, and the credential harvest that followedSandbox escape kill chain: package-caching proxy zero-day, lateral movement, stolen credentials, and remote code execution on Hugging FaceDetection gap: who noticed, when, and why logs without an owner are storage rather than detectionA second escape after the August 18...

  ListenShow Notes
• Episode #8

  MCP's By-Design RCE Heads to Vegas

  Jul 7, 202614 minS1

  <p>Anthropic's decision to treat a systemic remote code execution flaw in its MCP SDK as expected behavior rather than a bug opens this episode, followed by a preview of Black Hat USA 2026 and DEF CON 34's AI-heavy briefings.</p>OX Security's April 2026 disclosure of an unauthenticated RCE spanning all four official MCP SDK languages, including the LangFlow takeoverA Black Hat briefing showing Anthropic, Google, and OpenAI agents sharing the same trust-handoff failure, plus a 30B open model outperforming frontier models at exploitationDEF CON 34's theme "Agency" and AI Village's new poster track on adversarial attacks against agentic systemsHalCTF, the...

  ListenShow Notes
• Episode #7

  GLM-5.2 Ate the Export Controls for Breakfast

  Jun 30, 202618 minS1

  <p>This episode examines how GLM-5.2, an open-weight model from Z.ai, outperformed Claude Code on IDOR vulnerability detection one day after U.S. export controls targeted equivalent frontier models — and what that means for defenders.</p>Benchmark breakdown: GLM-5.2 scored 39% F1 against Claude Code's 32% on Semgrep's IDOR benchmark, at $0.17 per findingGovernance architecture failure: MIT-licensed, locally deployable weights produce no provider-side telemetry and cannot be recalled the way API keys can be revokedActive exploitation: Russian-language forums circulated jailbreaks within days of release; Travis Lanham of Armadin described the model as enabling attacker-grade lateral movement with zero visibilityCompressed timelines: Dario Amodei's si...

  ListenShow Notes
• Episode #6

  Five Eyes Named Your Agent Stack a National Security Risk

  Jun 23, 202618 minS1

  <p>On June 22, 2026, the Five Eyes alliance published a joint advisory warning that frontier AI will transform offensive cyber capabilities within months, not years — signed by the NSA Cybersecurity Director and acting CISA Director.</p>Five Eyes escalation pattern: Three coordinated actions in six weeks, from the May agentic AI risk framework to the June joint statement naming specific commercial modelsAgentic kill chain: The May guide's five risk buckets and 23 distinct risks, with focus on privilege abuse, agent autonomy, and credential scopeExport control sequencing: The June 12 Commerce Department directive restricting Fable 5 and Mythos 5, and how it removed defender access while ad...

  ListenShow Notes
• Episode #5

  IronWorm Ate Your AI Keys

  Jun 16, 202619 minS1

  <p>This episode covers the IronWorm campaign, a Rust-based infostealer that compromised 36 npm packages in the Arweave/WeaveDB ecosystem by hiding a native Linux binary behind preinstall hooks and backdating commit timestamps up to 13 years.</p>Kill chain mechanics: custom UPX stub, per-call-site string encryption, eBPF rootkit hiding processes from the kernel, and OIDC Trusted Publishing abuse enabling self-replication through CICredential targets: 86 environment variables covering AWS, GitHub, SSH keys, and the full AI provider stack — Anthropic, OpenAI, and Gemini — framed as an agent takeover surface, not just a billing riskAttribution and toolchain: commit pattern overlap with Shai-Hulud, no shared code, and...

  ListenShow Notes

Based on semantic analysis of episode topics and host coverage, this show is a strong guest fit for executives in:

Industry fit is computed by PitchCentric using vector embeddings of the show's episode catalog.