Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-04T22:30:34.253827Z
Paper Citation Record · LEDGER
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
As of 20 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 8 inbound Pith citation observations for arXiv:2509.07315.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-04T05:54:53.426020Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-02T22:17:26.189855Z
Reference resolution
15 of 15 outbound references displayed
- verified exact0
- verified fuzzy8
- unresolved7
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 2050139c-1a41-4dc2-8342-07398f929c80 · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.638129Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 75380eee-d842-40d7-a7ba-246666bae247 · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 2
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.617520Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c67cf03c-def7-41f4-8a9b-f17e657514bd · outbound
This paper cites List of APPs: {app_list} Table 6: Prompts to generate the commonly used func- tions in each APP.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs List of APPs: {app_list} Table 6: Prompts to generate the commonly used func- tions in each APP
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.592795Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a44b9421-5187-4cb8-a250-c531f5d25167 · outbound
This paper cites Risk Categories:.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Risk Categories:
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.439571Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 8eb0e722-b5c9-413d-89f7-ea14220ae1cd · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.570784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ff37ea1c-1f92-4da2-80ca-7460304dd5a5 · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.547763Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 80007074-a3b9-4c4e-bb3a-d5d770d94db9 · outbound
This paper cites app_name.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs app_name
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.528537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 514a2bb1-c8a3-4152-b131-b79b9c823947 · outbound
This paper cites Please ensure the instructions are natural and realis- tic as if a user were speaking or typing them to trigger the API calls.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Please ensure the instructions are natural and realis- tic as if a user were speaking or typing them to trigger the API calls
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.505886Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6d97bd0d-e762-405d-9ae5-10d0fafcf43a · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.484173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fceeccb2-8993-4591-a673-67297cdae663 · outbound
This paper cites an unresolved cited work.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-04T22:30:34.463400Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 73f460c4-952c-440a-8dea-024bc4e0cea3 · outbound
This paper cites Privacy breaches may include but are not limited to, unintended exposure of the user’s identity information, financial data, medical records, communication contents, etc.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Privacy breaches may include but are not limited to, unintended exposure of the user’s identity information, financial data, medical records, communication contents, etc
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.415804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5220a71f-559e-42fb-bd91-b1d216e6a7ba · outbound
This paper cites For example, the model may inadvertently trigger or directly execute large bank transfers, payment requests, or recurring transactions.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs For example, the model may inadvertently trigger or directly execute large bank transfers, payment requests, or recurring transactions
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.392092Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7c69ebd2-991b-4860-8e33-b457d6f75ab8 · outbound
This paper cites If these operations are not properly safety-checked or fail to foresee potential issues, they may trigger unsafe behaviors that result in physical injury.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs If these operations are not properly safety-checked or fail to foresee potential issues, they may trigger unsafe behaviors that result in physical injury
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.369570Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3a5153c2-e867-4061-b00b-c2e400db9149 · outbound
This paper cites in- struction.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs in- struction
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-04T22:30:34.340435Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 64717eeb-59d7-4c39-9848-cadf5261bfce · outbound
This paper cites Safety Assessment of Chinese Large Language Models.
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs Safety Assessment of Chinese Large Language Models
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T22:30:34.155084Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 26540f43-af16-4e7e-bb42-cb33189006f4 · inbound
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use cites this paper.
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T05:54:53.426020Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95508fda-bf94-430c-a71d-f7a90d1ee718 · inbound
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis cites this paper.
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T21:18:17.102437Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation db1b3e41-99d2-49b5-9100-739846f540a9 · inbound
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis cites this paper.
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T22:03:02.643434Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d483be65-f2a2-4b3f-bcac-69127812b014 · inbound
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode cites this paper.
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 1
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T17:13:01.171575Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e1ef2c08-0e70-4678-b327-3718a55b296e · inbound
Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents cites this paper.
Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 55
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T01:43:56.686578Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation b843ab4b-6485-49c4-b757-1c8d8e28238a · inbound
Memory-Induced Tool-Drift in LLM Agents cites this paper.
Memory-Induced Tool-Drift in LLM Agents SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 38
- Resolution
- verified exact
- arxiv_id, observed 2026-06-30T00:24:04.405169Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a6f2d081-73ad-43dd-949e-bab350067458 · inbound
ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents cites this paper.
ForesightSafety-SAGE:A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 27
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T22:17:26.191427Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 1672d1f7-f840-4c5a-88d9-0909195994ad · inbound
Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents cites this paper.
Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T13:32:29.176874Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.