- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper investigates tool-result misbinding in LLM agents, where legitimate tool outputs are replayed in incorrect execution contexts, potentially causing unsafe actions. The authors introduce ReplayBench, covering 19 scenarios, four failure types, and three replay mechanisms. Experiments across eight LLMs and three agent frameworks reveal substantial vulnerabilities, with an average final-state error rate of 64.9% under cross-task replay. The paper further evaluates runtime defenses that effectively prevent replay-induced errors in the tested settings.
Critical strengths
-
The paper identifies a practical and underexplored vulnerability arising from incorrect tool-result attribution rather than malicious content, offering useful insights into agent safety.
-
The benchmark covers multiple models, frameworks, and failure scenarios. The stage-wise analysis and defense experiments further strengthen the empirical contribution.
Critical weaknesses
-
The experiments primarily rely on controlled replay mechanisms in sandbox environments. Additional evidence from realistic deployment settings would strengthen the practical significance.
-
The full benchmark and defense evaluations use relatively limited model–framework configurations. Broader validation would improve confidence in the generalizability of the findings.
Questions for authors
-
Could the authors clarify whether the observed vulnerabilities persist under stricter task instructions requiring fresh tool verification?
-
The related work discussion could be strengthened by incorporating relevant studies on agent security, execution reliability, and efficiency, including ToolSandbox, Sponge Tool Attack, AgentPoison, τ-bench, and a survey titled Efficiency in LLM Multi-Agent Systems: A Survey. These works provide complementary perspectives on adversarial tool use, persistent information risks, stateful evaluation, and efficiency trade-offs.
4 comments
Response to Reviewer Ps9T (Part II)
W1: Evidence from realistic deployment settings
A1: Thank you for this suggestion. We have added an end-to-end MCP case study to provide evidence beyond controlled sandbox replay (Section 4.4, p. 10, Lines 516–530; Appendix N, pp. 37–38, Lines 1949–2029).
We deploy a real MCP server with two independent clients sharing a StreamableHTTP transport implemented using MCP TypeScript SDK 1.25.3. Under concurrent requests with the same JSON-RPC ID (42), Task B receives Task A's genuine verification result while Task A times out. Identical response hashes confirm that the result is unchanged but misrouted. We further connect the clients to GPT-5.5 through the OpenAI Agents SDK. The target agent consumes Task A's result and invokes mock_send_email on attachment A instead of the requested attachment B. The runtime accepts the action, and an independent checker confirms a final-state error (FSER = 1/1). Importantly, this behavior is consistent with the real-world vulnerability documented in CVE-2026-25536, which identifies cross-client response misrouting in the official MCP TypeScript SDK.
We additionally verify that the failure persists under an explicit target-specific instruction, while clean and timing controls complete normally. These results demonstrate end-to-end feasibility of replay-induced misbinding in an MCP deployment configuration, rather than only in our benchmark replay mechanism.
W2: Broader model–framework validation
A2: Thank you for highlighting the importance of broader evaluation coverage. We have expanded both the primary T01 evaluation and the RCG defense evaluation.
Primary evaluation. We added CrewAI as a fourth agent framework, expanding T01 evaluation to 8 models × 4 frameworks × 7 scenarios (224 configurations). Among these, 94/224 configurations (42.0%) reach FSER = 1.00, with a mean FSER of 0.687 (Table 1, p. 6, Lines 271–303; Section 4.2.1, p. 7, Lines 346–354).
Expanded RCG evaluation. We evaluated three models (GPT-5.5, GPT-5.6-Luna, and Gemini-3.8-Flash) across three frameworks (LlamaIndex, LangGraph, and OpenAI Agents SDK), two scenarios (Email and Files), and four replay templates (T01–T04), with 10 replay and 10 clean trials attempted per configuration.
| Model | Replay Attempted | Replay Valid | RCG FSER | Clean SR |
|---|---|---|---|---|
| GPT-5.5 | 240 | 239 | 0/239 | 240/240 |
| GPT-5.6-Luna | 240 | 231 | 0/231 | 237/237 |
| Gemini-3.8-Flash | 240 | 238 | 0/238 | 239/239 |
| Total | 720 | 708 | 0/708 | 716/716 |
Across all 708 valid replay trials, RCG achieves DAR = 1.00, AAR = 0, and FSER = 0, while all 716 valid clean trials complete successfully. The 12 invalid replay trials and 4 invalid clean trials are separately accounted for (Appendix M.2.3–M.2.6, pp. 33–36, Lines 1761–1931).
These expanded results provide stronger evidence that replay vulnerabilities persist across diverse model–framework configurations, while RCG consistently prevents replay-induced persistent-state errors in the evaluated settings without sacrificing valid clean-task completion.
I thank the authors for the valuable rebuttal. I believe discussing on those realistic deployment and stricter settings would significantly enhance the credibility of this work and its applicability in various situations.
Most of my concerns are resolved, so i tend to maintain my positive rating to support acceptance of this paper.
A few small things:
- Some typos. E.g., Page3, Line118: an real result - > a real result; Page6, Line319: replay template -> replay templates.
- Some descriptions are inconsistent. E.g., Page10, Lines 501-505: It was stated that the defense level of FSER is 95.8%, but then it was mentioned that this number decreased from 92.1% to 0%; Page29, Lines 1540-1541: The text states that the table also reports “clean-task completion under explicit fresh verification”. However, if I understand it correctly, the table only contains data related to replay FSER.
Response to Reviewer Ps9T
We sincerely thank the reviewer for the positive feedback and continued support ! We appreciate the careful reading and helpful suggestions. We have corrected both typos and resolved the numerical and table-description inconsistencies identified in the comments. Thank you again for helping us improve the clarity and accuracy of the paper !!!
Response to Reviewer Ps9T (Part I)
Thank you for your great efforts in reviewing this paper and for your recognition of our work. We will try our best to answer all your questions. Please let us know if you still have further concerns, or if you are not satisfied with the current responses, so that we can further update the response ASAP.
Q1: Could the authors clarify whether the observed vulnerabilities persist under stricter task instructions requiring fresh tool verification?
A1: Thank you for raising this important question. We have added a dedicated evaluation in Appendix L (pp. 28–29, Lines 1494–1558) comparing three instruction conditions: Natural Prompt, Pre-action Evidence Validation Prompt, and Explicit Fresh Verification Prompt.
Experimental configuration: GPT-5.5 with LlamaIndex, covering five configurations (Email/T01 and Files/T01–T04), with 10 replay trials and 10 clean trials per configuration under each instruction condition.
As shown in Table 21 (p. 29, Lines 1513–1521), both strengthened instructions reduce aggregate FSER from 45/50 to 30/50. They eliminate T01 errors but fail to prevent replay-induced errors in T02–T04 (30/30). All clean trials complete successfully. Moreover, none of the 50 replay trials under explicit fresh verification obtains genuinely fresh evidence, despite 10 trials retrying the verification tool (Appendix L, p. 29, Lines 1534–1558).
These results demonstrate that stronger task instructions can mitigate cross-task misbinding but cannot reliably prevent stale-context, duplicate-effect, or out-of-order replay. Fresh verification requirements alone cannot guarantee that the underlying tool interface returns valid, context-bound evidence.
Q2: The complementary related work discussion
A2: Thank you for these helpful suggestions. We have expanded the Related Work discussion in Appendix A (p. 15, Lines 756–792) to incorporate all five recommended studies and clarify their connections to our work.
Specifically, we discuss:
These additions strengthen the discussion of agent security, persistent-state risks, stateful evaluation, and execution efficiency, while clarifying how ReplayBench complements existing studies by focusing on the misbinding of genuine and unmodified tool results across execution contexts.