Demo green, prod wrong: failure types founders should name
From Christian Tech Founder Show · 26:09
Show by Phoenix Dataworks
Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!Sources:• OWASP Top 10 — https://owasp.org/www-project-top-10-for-large-language-model-applications/• OWASP Prompt Injection — https://cheatsheetseries.owasp.org/cheatsheets/LLM_Prompt_Injection_Prevention_Cheat_Sheet.html• Check Point PuzzleMask — https://research.checkpoint.com/2026/puzzlemask-abusing-plain-prose-as-a-covert-ai-attack-vector/• Invariant Labs MCP poisoning — https://invariantlabs.ai/blog/mcp-security-notification-tool-poisoning-attacks• Embrace The Red SpAIware — https://embracethered.com/blog/posts/2024/chatgpt-macos-app-persistent-data-exfiltration/• PoisonedRAG — https://www.usenix.org/conference/usenixsecurity25/presentation/zou-poisonedrag• Authorization-First Retrieval — https://aclanthology.org/2026.trustnlp-main.15/• Pillar Security Deadbugz — https://www.pillar.security/blog/deadbugz-currently-active-mcp-supply-chain-campaign• APIsec Labs A2A peers — https://labs.apisec.ai/research/articles/hijacking-google-adk-malicious-a2a-peers/• OpenAI Hugging Face report — https://openai.com/index/hugging-face-incident-and-the-road-ahead/• Wiz Off Guard — https://www.wiz.io/blog/off-guard-breaking-litellm-from-authentication-bypass-to-cloud-compromise• CISA KEV alert — https://www.cisa.gov/news-events/alerts/2026/09/02/cisa-adds-seven-known-exploited-vulnerabilities-catalog• Anthropic Threat Intelligence — https://www.anthropic.com/threat-intelligence-report-september-2026• Anthropic cybersecurity evals — https://www.anthropic.com/research/investigating-incidents-cybersecurity-evals• Stochasticity in Agentic Evaluations — https://arxiv.org/html/2512.06710v1• OSWorld-Verified — https://xlang.ai/blog/osworld-verifiedChapters:00:00:00 Intro music00:00:06 Cold open00:01:44 Definitions00:03:43 Why agents need a different map00:04:29 Family 1: Injection00:06:42 Family 2: Tool abuse00:08:46 Family 3: Context and memory00:10:24 Family 4: RAG and vector stores00:12:21 Family 5: Connectors and MCP00:13:54 Family 6: Multi-agent handoffs00:15:51 Family 7: Auth gaps00:17:27 Family 8: Exfiltration via tools00:18:49 Family 9: Fake complete00:20:14 Family 10: Nondeterminism00:21:17 Ship gate for a small team00:23:47 Homework00:24:57 Close
More episodes of Christian Tech Founder Show
More episodes
- Draft, don't block: AI agents that make a reasonable assumption and flag it
- The Factory Floor leaderboard: why we benchmark AI coding agents, and how to build a benchmark you can trust
- MCP explained for founders: why connectors beat clicking, and where they break
- Stop being the human router (Grok Bot ops C)
- Skill is how. Routine is when. (Grok Bot ops B)
- Your AI teammate needs a job, not a personality
- Jev and System One: Typed Decisions, Confidence Gates, and When Humans Still Decide
- AI Harness 101: Context, Skills, Gates, and Clean-Pass Confidence
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.