View this page in English?Switch to English
    Langsung ke konten
    Gaincontrol

    Keamanan agentik, dibahas dari arsitekturnya.

    Tulisan teknis tentang keamanan agen AI, tata kelola identitas, dan eksekusi deterministik, dari tim yang membangun lapisan kendalinya. Lihat pemetaan ke NIST AI RMF, MITRE ATLAS, dan OWASP LLM Top 10.

    Terbaru3 menit baca

    Authenticating the agent isn't authenticating the action

    "Which agent is this" and "is this action allowed right now" are different questions. Most systems built for agent authentication only ever answer the first one, and treat that as settling the second.

    • 3 menit baca

      What a tamper-evident audit trail actually has to prove

      Most "audit logs" built for AI agents are mutable, editable by whoever already has database access, and easy to doctor without leaving a trace. Tamper-evidence is a specific, checkable property, not an adjective a vendor can just claim.

    • 4 menit baca

      What a kill switch has to decide before anyone presses it

      "We have a kill switch" sounds solved until you ask what it has to stop mid-flight, how fast, and what state it leaves behind. The button is the easy part. The decisions that make it meaningful happen long before anyone presses it.

    • 3 menit baca

      Contain prompt injection where the agent acts

      Most prompt-injection defenses try to filter what an agent reads. The risk only materializes once something downstream is willing to act on what it read, which makes authorizing the action the control that actually holds.

    • 3 menit baca

      Why MCP tool calls need checking at call time

      The tool schema an agent reads at discovery is a promise. Nothing in MCP stops a server from serving a different schema by the time that tool is actually called, so the check that closes the gap runs on the call itself.

    • 3 menit baca

      What deny by default costs on every tool call

      Authorizing every tool call before it leaves the agent is only as good as what the check costs. The choice between a network hop to a policy service and an in-process check decides whether deny by default survives production.

    • 6 menit baca

      MCP governance: six controls for enterprise integrations

      MCP standardizes how agents reach tools and data, but the protocol itself is not a security boundary. Enterprises need a governance layer across scoping, authorization, credentials, third-party risk, data boundaries, and audit.

    • 3 menit baca

      The blank-check problem: how agents inherit authority

      Agents don't arrive with authority of their own. They borrow a service account, an API key, or a human's session, and start acting under it. Unscoped inheritance is what turns an agent into a blank check with a user interface.

    • 3 menit baca

      Scoping agent authority with leases

      Static role-based access control assumes an actor that holds still long enough for a role to describe it. Agents don't, so their authority has to be scoped to the task and expire with it.

    • 3 menit baca

      What is agentic AI security?

      "AI security" and "agentic AI security" sound like the same category. They're not. One centers the model; the other centers what the model is authorized to do once it can act.

    • 2 menit baca

      Threat-modeling the MCP server path

      Model Context Protocol standardized how agents call tools, and quietly became the default path most agent actions now take to reach the outside world. Few teams have threat-modeled it.