View this page in English?Switch to English
    Langkau ke kandungan
    Gaincontrol

    Keselamatan agentik, dihujahkan dari seni binanya.

    Penulisan teknikal tentang keselamatan ejen AI, tadbir urus identiti dan pelaksanaan deterministik, daripada pasukan yang membina lapisan kawalannya. Lihat pemetaan kepada NIST AI RMF, MITRE ATLAS dan OWASP LLM Top 10.

    Terkini3 minit bacaan

    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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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 minit bacaan

      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.

    • 2 minit bacaan

      Shadow agents and the missing agent inventory

      Many organizations can't produce a complete list of the AI agents running in their environment. The ones that matter most are the ones nobody registered.

    • 3 minit bacaan

      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 minit bacaan

      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.