SecureClaw: Clawing Back Control of LLM Agents
SecureClaw dual-bounds LLM agents by confining plaintext via opaque handles at the read boundary and enforcing authorized previews at the action sink, achieving near-zero attack success with preserved utility.
Published 2026Paris Poster Session 6 · Fri, Dec 11, 2:30 PM–4:30 PM local time · Paris Poster HallarXiv ↗OpenReview ↗
Only vote on papers you've read. Sign in with GitHub to vote.
SecureClaw delivers a rigorous dual-boundary architecture that achieves near-zero attack rates and introduces bounded summaries as an explicit declassification interface, though its effectiveness depends on a trusted gateway and real-world handle durability remains unproven.
Abstract
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene. Existing defenses usually protect one boundary, either the planner/runtime or the action sink, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that places authorization at the effect sink and plaintext confinement at the read boundary. Sensitive reads pass through a trusted gateway that replaces raw values with opaque handles and, in the evaluated deployment, bounded summaries as an explicit declassification interface. Writes that change external state follow a PREVIEW$\rightarrow$COMMIT protocol in which only a trusted executor may commit the exact canonical request authorized by policy. The runtime can still plan over summaries and symbolic references, but cannot directly dereference secrets or perform side effects. Across AgentDojo, AgentLeak, and Agent Security Bench (ASB), SecureClaw is the only defense we evaluate in a common harness that simultaneously retains usable task utility and achieves 0\% attack success rate (ASR) on ASB, 0.64\% ASR on AgentDojo, and 3.23\% overall leak on AgentLeak's attacked parity lane, which measures final-output and internal-relay leakage.