# SecureClaw: Clawing Back Control of LLM Agents

arXiv: https://arxiv.org/abs/2606.09549 · HTML: https://mlsanity.com/paper/2606.09549/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 14 of 14)

- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks](https://mlsanity.com/paper/2504.18575/) (2025)
- [Progent: Securing AI Agents with Privilege Control](https://mlsanity.com/paper/2504.11703/) (2025)
- [Securing AI Agents with Information-Flow Control](https://mlsanity.com/paper/2505.23643/) (2025)
- [A Survey on Trustworthy LLM Agents: Threats and Countermeasures](https://mlsanity.com/paper/2503.09648/) (2025)
- [DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents](https://mlsanity.com/paper/2506.12104/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [ACE: A Security Architecture for LLM-Integrated App Systems](https://mlsanity.com/paper/2504.20984/) (2025)
- [IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents](https://mlsanity.com/paper/2508.15310/) (2025)
- [Formal Policy Enforcement for Real-World Agentic Systems](https://mlsanity.com/paper/2602.16708/) (2026)
- [Faramesh: A Protocol-Agnostic Execution Control Plane for Autonomous Agent Systems](https://mlsanity.com/paper/2601.17744/) (2026)

## Built on by (most cited first, 2 of 2)

- [Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows](https://mlsanity.com/paper/2609.31301/) (2026)
- [Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift](https://mlsanity.com/paper/2609.37475/) (2026)

## Abstract (arXiv)

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 point where external actions are executed, and therefore do not by themselves secure both surfaces. We present SecureClaw, a dual-boundary architecture that enforces authorization in a trusted executor and keeps raw protected data outside the LLM runtime. Sensitive reads pass through a trusted gateway that replaces raw values with reference IDs. In the evaluated deployment, the gateway also provides short planning summaries that deliberately release selected information, a process called declassification. Writes that change external state follow a PREVIEWrightarrowCOMMIT protocol in which only a trusted executor may execute the exact request authorized by policy. The runtime can still plan over summaries and reference IDs, but cannot directly resolve the IDs into secrets or perform side effects. Across the AgentDojo, AgentLeak, and Agent Security Bench (ASB) benchmarks, 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. Code is available at https://github.com/ponyyuhan/SecureClaw.