{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=tE2z8-hqoLY",
  "slug": "beyond-the-lethal-trifecta-agentic-commerce-on-the-open-internet-david-l-0ps6jqq",
  "url": "https://feed7.dev/p/beyond-the-lethal-trifecta-agentic-commerce-on-the-open-internet-david-l-0ps6jqq",
  "title": "Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet — David Levine, Kiduna Club",
  "why_included": "This talk proposes legally registered agent organizations, scoped JWT authority, and blockchain audit trails for open-internet commerce; it is an architecture proposal, not validation.",
  "summary": "The talk frames the “lethal trifecta” as agents combining private data, untrusted internet content, and action permissions. It proposes a registered **DUNA**, scoped **JWT tokens**, and blockchain-linked audit trails to establish agent identity, authority, and boundaries.",
  "practical_implication": "Builders can borrow the narrower design principle now: give every agent explicit organizational identity, short-lived scoped claims, bounded account access, and a traceable owner before it interacts with another agent or external service.",
  "agent_context": "The talk frames the “lethal trifecta” as agents combining private data, untrusted internet content, and action permissions. It proposes a registered **DUNA**, scoped **JWT tokens**, and blockchain-linked audit trails to establish agent identity, authority, and boundaries.\n\nBuilders can borrow the narrower design principle now: give every agent explicit organizational identity, short-lived scoped claims, bounded account access, and a traceable owner before it interacts with another agent or external service.\n\nThe presentation reports organization number **628407**, but supplies no deployment study, security testing, or evidence that the scheme prevents prompt injection or data leakage. Decision markets and broad autonomous commerce remain proposed mechanisms in this material.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=tE2z8-hqoLY",
    "published_at": "2026-09-01T20:30:27.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "security"
  ],
  "topics": [
    "multi-agent",
    "agent-reliability",
    "tool-use"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The presentation reports organization number **628407**, but supplies no deployment study, security testing, or evidence that the scheme prevents prompt injection or data leakage. Decision markets and broad autonomous commerce remain proposed mechanisms in this material."
  ],
  "connected_context": {
    "meaning": "This extends the candidates’ least-privilege guidance from individual tool calls to cross-organization agent identity, proposing scoped credentials, accountable ownership, and shared audit trails. It remains an architectural proposal rather than evidence of protection: identity and traceability may bound authority, but the supplied material does not show that they stop prompt injection, leakage, manipulation, or unauthorized commerce.",
    "corpus_size": 669,
    "generated_at": "2026-09-03T10:00:24.898Z",
    "connections": [
      {
        "title": "Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypal",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=vGn6N4-bxBY",
        "feed7_url": "https://feed7.dev/p/your-agent-just-authorized-what-jay-mok-ben-coumes-paypal-024znqi",
        "reason": "PayPal’s consequence-scaled, independently verifiable mandates provide a closer authorization model for the proposed scoped JWT claims, while both leave the highest-risk interoperable mechanism unproven."
      },
      {
        "title": "Teaching agents to pay — Anna Spysz, Stripe",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=A-zeQiYkmXk",
        "feed7_url": "https://feed7.dev/p/teaching-agents-to-pay-anna-spysz-stripe-04jxy0s",
        "reason": "Stripe adds provider-enforced spending limits, cancellation, and decision logs as implementation consequences; these controls remain necessary even when an agent has a registered identity and scoped token."
      },
      {
        "title": "The Agentic Web and the Bazaar Era of AI - Ramesh Raskar, MIT Media Lab",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=sum9DgexFRQ",
        "feed7_url": "https://feed7.dev/p/the-agentic-web-and-the-bazaar-era-of-ai-ramesh-raskar-mit-media-lab-0ddd8pc",
        "reason": "Project Nanda proposes complementary open discovery, identity, and coordination layers across vendors, placing the DUNA-and-token scheme within a broader agent-network architecture that can be tested layer by layer."
      },
      {
        "title": "Unlock Agent Autonomy: The Runtime for AI-Native Systems — Tushar Jain, Docker",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=zaGyGgLW3SM",
        "feed7_url": "https://feed7.dev/p/unlock-agent-autonomy-the-runtime-for-ai-native-systems-tushar-jain-dock-0wg72se",
        "reason": "Docker’s runtime containment and policy outside the model supply an enforcement boundary that organizational identity and audit trails alone do not provide; both approaches remain architectural directions without validated protection."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-01T20:30:27.000Z",
  "modified_at": "2026-09-01T20:30:27.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/beyond-the-lethal-trifecta-agentic-commerce-on-the-open-internet-david-l-0ps6jqq",
    "json": "https://feed7.dev/p/beyond-the-lethal-trifecta-agentic-commerce-on-the-open-internet-david-l-0ps6jqq.json",
    "markdown": "https://feed7.dev/p/beyond-the-lethal-trifecta-agentic-commerce-on-the-open-internet-david-l-0ps6jqq.md"
  }
}