Om denne podcast
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.
Episoder
- Agent 365 Still Has Blind Spots · 20 min. · Sæson 1 Episode 15This episode of Autonomous Autopsy examines Microsoft's Agent 365, which reached general availability on May 1, 2026, and is featured as an observability layer for agents at the…
- The Intern Who Only Heard Go On · 20 min. · Sæson 1 Episode 14This episode examines Operation Snowball, a case documented by Malbear Labs in which a jailbroken DeepSeek Flash agent carried out roughly two weeks of intrusion work against a…
- Shadow Agents Get a Badge · 20 min. · Sæson 1 Episode 13This episode examines how malicious OpenClaw skills and leaked agent tokens created a shadow AI agent problem, and what Microsoft's planned extension of Entra Agent ID to unknown…
- The AGENTS.md That Stole Keys · 19 min. · Sæson 1 Episode 12This episode of Autonomous Autopsy examines a plaintext AGENTS.md file, caught in the wild by Forever Security, that used indirect prompt injection to steer a coding assistant…
- The Lone Hacker's Open Dashboards · 19 min. · Sæson 1 Episode 11This episode of Autonomous Autopsy examines a Reuters-reported campaign in which one Chinese-speaking operator used the open-source Cairn agent toolkit to attempt about 1,200…
- The Gateway With No Lock · 19 min. · Sæson 1 Episode 10This episode of Autonomous Autopsy examines CVE-2026-59822, an improper authentication flaw in BerriAI LiteLLM that CISA added to its Known Exploited Vulnerabilities catalog on…
- Nobody Was Holding the Leash · 20 min. · Sæson 1 Episode 9This 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…
- MCP's By-Design RCE Heads to Vegas · 14 min. · Sæson 1 Episode 8Anthropic'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…
- GLM-5.2 Ate the Export Controls for Breakfast · 18 min. · Sæson 1 Episode 7This 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…
- Five Eyes Named Your Agent Stack a National Security Risk · 18 min. · Sæson 1 Episode 6On 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…
- IronWorm Ate Your AI Keys · 19 min. · Sæson 1 Episode 5This 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…
- Your AI Assistant Is Now the Attack Surface · 19 min. · Sæson 1 Episode 4This episode covers the TeamPCP supply chain campaign of May 2026, in which attackers hijacked TanStack's CI/CD pipeline to publish 84 malicious npm packages with valid SLSA…
- Trivy Was the Key the Whole Time · 22 min. · Sæson 1 Episode 3This episode covers the March 24, 2026 supply chain compromise of LiteLLM, a widely used AI proxy library with over 95 million monthly downloads, in which attackers backdoored…
- Anthropic Called the RCE a Feature · 21 min. · Sæson 1 Episode 2This episode covers OX Security's April 2026 advisory exposing a design-level remote code execution flaw in Anthropic's MCP STDIO interface, affecting an estimated 200,000…
- Shadow Agents at Scale · 20 min. · Sæson 1 Episode 1This episode examines the structural security gap between what enterprise teams believe about their AI agent deployments and what is actually running, anchored by the n8n supply…








