{ "drafts": [ { "id": "p1-entity-swap", "snippets": { "S1": "A user-space kernel implements an application kernel.", "S2": "The interceptor handles system calls from the sandboxed application." }, "draft": "## Kernels\n\nA user-space kernel implements an application kernel [S1]. The Hypervisor component handles system calls from the sandboxed application [S2].", "expected": [ true, false ], "attack": "entity swap: an uncited Hypervisor is inserted" }, { "id": "p2-negation-flip", "snippets": { "S1": "Denylists are not a security boundary.", "S2": "The agent never sees the real key." }, "draft": "## Denylists\n\nDenylists are a security boundary [S1]. The agent never sees the real key [S2].", "expected": [ false, true ], "attack": "negation removed from a sourced claim" }, { "id": "p3-number-swap", "snippets": { "S1": "The sandbox policy allows 10 destinations." }, "draft": "## Policy\n\nThe sandbox policy allows 5 destinations [S1]. The sandbox policy allows 10 destinations [S1].", "expected": [ false, true ], "attack": "number changed" }, { "id": "p4-unsupported-claim", "snippets": { "S1": "microVM monitor is an open source virtual machine monitor that creates lightweight virtual machines called microVMs.", "S2": "Each microVM runs its own guest kernel." }, "draft": "## microVM monitor\n\nmicroVM monitor is an open source virtual machine monitor that creates lightweight virtual machines called microVMs [S1]. microVM monitor guarantees that no agent can ever exfiltrate data over the network [S1]. Each microVM runs its own guest kernel [S2].", "expected": [ true, false, true ], "attack": "claim cites a real snippet that does not support it" }, { "id": "p5-dangling-and-uncited", "snippets": { "S1": "Any process that can write to this socket can ask the daemon to start new containers with any settings, including a container that mounts the host root filesystem.", "S2": "A proxy outside the sandbox checks the destination, adds the credential to the request and forwards it." }, "draft": "## Socket\n\nAny process that can write to the socket can ask the daemon to start new containers with any settings [S1]. The socket is safe to mount in production. A proxy outside the sandbox adds the credential to the request and forwards it [S2]. Mounting the socket is standard practice [S9].", "expected": [ true, false, true, false ], "attack": "uncited sentence and a citation to a snippet that does not exist" }, { "id": "p6-paraphrase-ok", "snippets": { "S1": "virtualized containers can use different hypervisors underneath, including microVM monitor.", "S2": "Each microVM runs its own guest kernel." }, "draft": "## virtualized containers\n\nvirtualized containers can use several hypervisors underneath, including microVM monitor [S1]. Every microVM runs its own guest kernel [S2].", "expected": [ true, true ], "attack": "none: faithful paraphrases must pass" } ] }