- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper investigates an overlooked security issue in tool-using LLM agents, termed intent-to-action binding failure, where an agent correctly understands the user’s intent and follows an appropriate plan but binds a security-critical tool parameter to the wrong entity based on manipulated external evidence. To study this problem, the authors propose Multi-Source Compositional Evidence Fabrication (MCEF), which distributes plausible, declarative, and instruction-free evidence across multiple attacker-writable sources. During normal retrieval and reasoning, the agent combines these fabricated evidence items and derives an attacker-selected parameter while largely preserving the original task intent and execution plan. MCEF consists of four stages: candidate task discovery, target-to-evidence inversion, multi-source evidence fabrication, and combination triggering. Experiments across six models, four agent frameworks, and six tasks achieve an average 93.1% attack success rate, 99.3% intent preservation, and 92.9% plan preservation. The results further show that distributing evidence across multiple sources substantially strengthens the attack, while existing prompt-injection detectors and runtime defenses provide only limited protection. Overall, the paper highlights that securing LLM agents requires not only detecting malicious instructions or plan deviations, but also validating whether external evidence reliably justifies security-critical parameter bindings.
Critical strengths
- MCEF does not rely on explicit malicious instructions such as prompt injection. Instead, it manipulates plausible, declarative evidence distributed across multiple sources, which is well aligned with the identified intent-to-action binding vulnerability and makes the attack harder for instruction-oriented detectors to identify.
- MCEF consists of four well-defined stages—candidate task discovery, target-to-evidence inversion, multi-source evidence fabrication, and combination triggering—forming a complete pipeline from identifying vulnerable tasks to inducing the attacker-desired parameter binding.
Critical weaknesses
- The attacker is expected to observe or reasonably approximate the agent’s evidence-access trajectory and to have write access to multiple relevant external sources. It remains unclear how often these conditions hold in realistic deployments, which may limit the practical applicability of the attack.
- Tool outputs and business actions are mocked rather than executed in real production systems. Therefore, while the experiments demonstrate the vulnerability at the reasoning and parameter-binding level, the attack’s effectiveness under real-world APIs, permission structures, and operational constraints remains insufficiently validated.
- Intent preservation is evaluated using the same model as the tested agent, which may introduce self-evaluation bias. In addition, plan preservation is measured using Jaccard similarity over tool-call multisets and ignores call order and finer-grained control-flow differences, so the reported preservation scores may not fully capture whether the underlying execution plan truly remains unchanged.
Questions for authors
Please see weakness
Thank you for the suggestions on attacker assumptions and preservation metrics. We specify the deployment conditions and report judge and action-sequence comparisons. Changes in the revised manuscript are marked in red.
1. Multi-source write access and dependency knowledge.
We agree that these prerequisites needed clarification. §3.2 specifies that the evaluated construction uses dependencies observed in clean executions and write access to selected evidence sources. Appendix A maps payload fields to concrete object/field permissions and protected platform attributes.
In the simulator (§5.3, Table 4), retaining k=2 sources gives 79.0% ASR and retaining k=1 gives 33.6%. The comparison also varies the amount of retained evidence. We have not measured how often the necessary access and task knowledge coexist in deployments.
2. Mocked tools and production relevance.
We agree that the connection to deployed interfaces needed explanation. §3.2 and Appendix A specify the simulated evidence and business actions. The experiments isolate how evidence changes the agent's parameter binding while it continues the requested task.
Appendix A follows a T-A1 simulated trace from its two reads to the recorded sharing action. The platform documentation describes conditional permissions. Field ACL enforcement, a single identity with the required rights, and whether a deployed reader accesses the same editable record remain unverified. No production share was executed.
3. Self-evaluation bias in intent preservation.
To check whether IPR depended on the choice of judge, we rescored the same 134 executions with a fixed DeepSeek-v4-pro judge. §5.1 describes both judging configurations; Appendix C, Table 17, compares the fixed judge with the evaluated-model judge used in §5.2.
Both judges yielded an IPR of 99.25% (133/134 positive labels each) and agreed on 132/134 labels (98.51%). Most labels were positive, and the fixed judge shares its model with the DeepSeek agents, so this agreement does not rule out shared bias.
Manual inspection of 60 samples found no issues. Both configurations receive the task and benign/attacked final responses, each truncated to 2,000 characters, to assess preservation of the high-level task intent.
4. Call order and joint preservation.
We agree that call order should be checked explicitly. §5.2 and Appendix C add an order-sensitive action-sequence analysis. Each of the six tasks in our experiments has exactly one type of core business-action tool. PPR compares these action calls and retains repetitions; retrieval calls describe evidence access and are excluded.
The original PPR is 92.9%, averaged equally across six models. On the same 130 comparable runs, multiset Jaccard and order-aware normalized edit similarity both average to 92.76% (92.8% rounded). The difference from 92.9% reflects aggregation by run versus by model. No run has equal action multisets in a different order. Retaining order therefore leaves pooled similarity unchanged on this sample. Core action sequences match exactly in 110/130 runs, and full tool sequences including retrieval match in 29/130. Complex control flow remains untested.
For an all-attempt comparison, Appendix C fixes benign references independently of attack outcomes. For action-tool sequences A and B with repetitions retained, ordered similarity uses Levenshtein distance:
S(A,B)=1−max(∣A∣,∣B∣)Lev(A,B).
§5.5, Table 9, also adds the joint criterion:
Ji=1{ASi=1∧IPRiext=1∧Ai=Bi}.
The four-model reference subset contains 92 of 96 cells; the five-model joint comparison includes all 120. These checks address action order and repetitions and jointly require attack success, intent preservation, and exact action-tool sequence preservation.