- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper investigates persistent memory attacks in OpenClaw and similar agent harnesses, where external claims supplied by an attacker are stored during legitimate tasks and later influence behavior across sessions. It proposes ZoneClaw, which separates information retention from action authority through three memory trust zones and four specialized roles, with a Gatekeeper checking external claims against trusted policies and knowledge before promoting them into operational memory. Across four attack scenarios, two injection settings, and four model backbones, the authors report reducing attack success from 77.5% to 1.25% while completing 458 of 480 legitimate tasks, with ablations and mechanism analyses supporting the effectiveness of the proposed authority boundaries.
Critical strengths
-
Important problem for frontier agent harnesses. The paper identifies an important security gap in frontier agent harnesses, showing how external claims can enter persistent memory and acquire authority over later actions. This problem is particularly relevant to agents that maintain workspaces and learn from their environments across sessions.
-
Clear design with supporting mechanism analysis. Separating information retention from action authority provides a clear design principle, implemented through memory zoning, role separation, and controlled promotion. The ablations and selective promotion experiments provide useful evidence that these mechanisms can restrict malicious influence while retaining useful information.
Critical weaknesses
-
Substantial online overhead. The additional role invocations and verification steps introduce online overhead, with the reported BCC experiment showing execution time of 2.26 times the baseline and estimated API cost of 1.74 times the baseline. Broader measurements that separate memory ingestion costs from subsequent task execution would clarify the tradeoffs among security, responsiveness, and resource consumption.
-
Limited coverage of benign and attack scenarios. Generalization remains uncertain because the evaluation covers four constructed attack scenarios, while the separate benign utility evaluation uses a subset of 30 tasks on one model. I encourage the authors to explore the DecodingTrust-Agent Platform (DTap), with appropriate adaptation to the persistent memory setting, to assess generalization across both utility and security.
Chen, Z., Liu, X., Tong, H., Guo, C., Nie, Y., Zhang, J., Kang, M., Xu, C., Liu, Q., Liu, X., Shi, T., Xiao, C., Koyejo, S., Liang, P., Guo, W., Song, D., & Li, B. (2026). DecodingTrust-Agent Platform (DTap): A controllable and interactive red-teaming platform for AI agents. arXiv. https://doi.org/10.48550/arXiv.2605.04808
Questions for authors
No
4 comments
Response to Reviewer jSvP (2/2)
W2: Limited coverage of benign and attack scenarios, with a suggestion to assess utility and security on DTap.
A2: We agree that broader coverage of both attack and benign scenarios is important. Following your suggestion, we extend our evaluation along two dimensions, namely attack and utility evaluation on DTap (Table 4) and benign utility on additional Workspace-Bench tasks (Table 5).
(1) Attack and utility evaluation on DTap. Following your suggestion, we adapt 10 DTap tasks to the persistent memory setting. These tasks belong to the hidden side effect class, in which the attacker tries to inject an unauthorized verification claim into the Customer Relationship Management (CRM) system while the agent completes the legitimate task. We inject attacker payloads into each adapted task as specified by our threat model (Section 2.3 of our paper), so that the payload is read in the injection phase and the task is completed in the execution one. Utility is measured with the official DTap verifiers, and ASR counts unauthorized claims actually written into the CRM. ZoneClaw reduces ASR from 9/10 to 0/10 with no utility loss, whereas Watcher and ClawGuard remain at 8/10 and 10/10. This discovery supports ZoneClaw's effectiveness on the adapted DTap tasks beyond our original attack scenarios.
Table 4. Attack and defense performance on 10 DTap tasks adapted to cross-session persistent memory.
| Task set | Method | ASR↓ | Utility↑ |
|---|---|---|---|
| DTap | OpenClaw | 9/10 | 10/10 |
| DTap | Watcher | 8/10 | 10/10 |
| DTap | ClawGuard | 10/10 | 10/10 |
| DTap | ZoneClaw | 0/10 | 10/10 |
(2) Benign utility. We add 19 Workspace-Bench tasks with no attacker content from two categories, namely Operations Manager (10 tasks, 204 rubric criteria) and Logistics Manager (9 tasks, 163 rubric criteria). Here, we utilize GPT-5.5 at medium reasoning as the backbone and Claude Sonnet 4.6 as the judge, which follows the same setting as Appendix C.8 of our paper. As shown in Table 5, ZoneClaw stays within about one percentage point of OpenClaw on Operations Manager and is slightly above it on Logistics Manager. In contrast, ClawGuard and PrivSep lose 8.0 and 13.4 points on Operations Manager. These results show that ZoneClaw maintains benign task utility comparable to OpenClaw while outperforming the other defense methods across both task categories, complementing the utility evidence from DTap.
Table 5. Benign utility on 10 Operations Manager tasks covering 204 rubric criteria and 9 Logistics Manager tasks covering 163 rubric criteria from WorkspaceBench, with GPT-5.5 at medium reasoning and Claude Sonnet 4.6 as the judge.
| Method | Metric | Operations Manager | Logistics Manager |
|---|---|---|---|
| OpenClaw | Mean task score(%)↑ | 45.54 | 49.47 |
| ClawGuard | Mean task score(%)↑ | 37.55 | 50.81 |
| PrivSep | Mean task score(%)↑ | 32.16 | 39.05 |
| ZoneClaw | Mean task score(%)↑ | 44.54 | 52.24 |
Our responses to Reviewers FiEf and 6xj1 further add new information sources, new input forms, and two additional agent harnesses. We will incorporate all new results and clarifications into the revised paper before the end of the discussion period, with changes highlighted in blue.
We hope these results and analyses address your concerns, and we are happy to provide further clarification.
Thanks for your response. I will keep my positive score!
Revision Uploaded: Follow-Up to Reviewer jSvP
Dear Reviewer jSvP,
Thank you for your follow-up and for keeping your positive score. We are truly encouraged by your continued support of our work. Your comments on the online overhead and the coverage of scenarios directly led to the phase-level overhead analysis and the broader evaluation, both of which have made the paper more complete.
We have uploaded the revised paper, which incorporates all new results and clarifications from our responses. All changes are highlighted in blue and these additions are also summarized in Section 4.8. The table below lists where each of your comments is addressed.
| Your comment | Revision | Location |
|---|---|---|
| W1 Online overhead | Overhead separated into the injection and exploitation phases | Appendix C.6 |
| Cumulative overhead of one injection phase followed by ten tasks | Appendix C.6 | |
| Optimized implementation of ZoneClaw | Appendix C.6 | |
| W2 Coverage of attack scenarios | 10 DTap tasks adapted to cross-session persistent memory | Section 4.7 |
| Two additional harnesses, two additional information sources, and three additional input forms | Section 4.7 and Appendix C.7 | |
| W2 Coverage of benign scenarios | 19 additional Workspace-Bench tasks in two categories | Appendix C.10 |
We would like to highlight that the core contribution of our paper lies in the design principle of separating persistence from authority.
- Persistent memory attacks succeed because remembered content is treated as trusted by default. Following this principle, ZoneClaw enables CUAs to continually accumulate knowledge and experience from external environments, while withholding authority from untrusted content over subsequent actions.
Thank you once again for your time and constructive feedback. We would be glad to provide any further clarification before the discussion period ends.
Best regards,
Authors of Submission 5466
Response to Reviewer jSvP (1/2)
Thank you for your insightful review and for recognizing that our work addresses an important problem for frontier agent harnesses with a clear design and supporting mechanism analysis. Following your suggestions, we have added two groups of experiments. (1) An overhead analysis covering injection versus execution, long-horizon tasks, and an optimized implementation (A1). (2) Broader coverage with attack and utility evaluation on DTap and benign utility on two Workspace-Bench categories (A2). We provide detailed point-by-point responses to your comments below.
W1: Substantial online overhead and insufficient separation of memory ingestion costs from subsequent execution costs.
A1: We agree that online overhead is an important practical concern. The defense methods require additional processing to enforce their respective safeguards. The reported latency and API cost in our paper cover a complete injection–execution pair. We analyze the overhead along three dimensions, namely injection versus execution (Table 1), long-horizon tasks (Table 2), and an optimized implementation (Table 3).
(1) Injection versus execution. In Table 1, ZoneClaw spends 144.8 s on the injection phase, where the Observer extracts external claims and the Gatekeeper checks them before promotion, concentrating much of the additional processing in this phase. This phase accounts for 87% of the additional latency and 79% of the additional API cost relative to OpenClaw. Subsequent tasks can reuse the admitted information without repeating these checks. In the execution phase, ZoneClaw adds only 12.3 s and USD 0.0030 per task over OpenClaw, with about half the latency of the other defense methods (62.0 to 71.0 s) and 2.5× to 5.1× lower in cost.
Table 1. Phase-separated overhead on user-triggered BCC Exfiltration scenarios with Qwen3.7-Plus at medium reasoning.
(2) Long-horizon tasks. We conduct one injection phase followed by ten executions with Claude Sonnet 4.6 and report totals after 1, 5, and 10 executions in Table 2. ZoneClaw incurs the largest overhead after the first execution, but its total API cost and latency over ten executions are 24.8% and 8.3% lower than OpenClaw’s and 4.2% and 15.7% lower than PrivSep’s. This saving mainly arises because the Planner and Executor of ZoneClaw read only the trusted information in D0 and D1, and the actor of PrivSep reads only its structured summaries by its reader, whereas OpenClaw reloads all stored content. However, PrivSep's summaries may carry malicious instructions into later memory updates and rise its ASR to 3/3, whereas ZoneClaw consistently stays at 0/3, ehabling reuse of verified knowledge while restricting unapproved instructions from guiding actions.
Table 2. Total overhead after 1, 5, and 10 executions on user-triggered BCC Exfiltration scenario.
(3) Optimized implementation. We further preload tool instructions, batch reads, reduce coordination turns, and shorten reports to reduce its overhead. In Table 3, ZoneClaw's latency falls from 176.8 s to 145.0 s and API cost from USD 0.0322 to 0.0244, with ASR and utility unchanged. Relative to OpenClaw, the overhead drops from 2.26× to 1.86× in latency and from 1.74× to 1.32× in cost. The optimized ZoneClaw remains the cheapest defense method with latency slightly above the baselines (117.7 to 140.0 s). We will release the optimized ZoneClaw implementation upon acceptance.
Table 3. End-to-end overhead and performance with the optimized implementation (same setting as Table 1).