statements ยท statement-BATCH-2026-006-030

source-BATCH-2026-005-007

The authors identify attack surfaces in system prompts, user inputs, tool interactions, and long-term memory retrieval.

Statement context

Statement type
interpretation
Exact source locator
arXiv:2410.02644v4 PDF pp. 1-2, Abstract, Figure 1, and Introduction
Source date
2024-10-03
Role at source time
joint authors of the ASB paper
Evidence character
author interpretation
Scope
The operational stages modeled by ASB.

Recorded uncertainty: The taxonomy reflects the benchmark design and may not exhaust real-world attack surfaces.

Indexed source: Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents

Evidence lineage and transparency

Relationship fieldLinked identifiers
topic idstopic-ai-agents, topic-ai-governance, topic-cybersecurity, topic-non-human-identity

Machine review: machine checked. Human review: approved. Workflow: published.

Complete structured record
statement id
statement-BATCH-2026-006-030
source id
source-BATCH-2026-005-007
person id
Unknown
institutional author
Zhang et al. (joint paper authors)
book edition id
Unknown
speaker role at source time
joint authors of the ASB paper
organization at source time
Zhejiang University and Rutgers University
statement type
interpretation
neutral paraphrase
The authors identify attack surfaces in system prompts, user inputs, tool interactions, and long-term memory retrieval.
direct quote
Unknown
direct quote rights note
Unknown
exact locator
arXiv:2410.02644v4 PDF pp. 1-2, Abstract, Figure 1, and Introduction
locator type
pdf_page
source date
2024-10-03
topic ids
topic-ai-agents, topic-ai-governance, topic-cybersecurity, topic-non-human-identity
executive role context
role-ciso, role-cio, role-cto, role-general-counsel, role-board-director
industry context
cross-sector
geographic context
synthetic benchmark; no human geography
evidence character
author_interpretation
factual verification status
attribution_verified
statement scope
The operational stages modeled by ASB.
uncertainty
The taxonomy reflects the benchmark design and may not exhaust real-world attack surfaces.
extraction method
Machine-assisted close reading of the exact verified source version; original neutral paraphrase; human review pending.
machine extraction confidence
0.94
independent agent review status
not_started
publication status
published
workflow status
published
machine review status
machine_checked
human review status
approved
reviewed by
Murray Newlands
reviewed at
2026-08-16T23:17:22Z
Provenance and revision history
{
  "provenance": [
    {
      "source_url": "https://arxiv.org/abs/2410.02644",
      "accessed_at": "2026-08-15",
      "retrieval_method": "Exact verified source version inherited from BATCH-2026-005 and statement-level close reading",
      "exact_locator": "arXiv:2410.02644v4 PDF pp. 1-2, Abstract, Figure 1, and Introduction",
      "content_hash": "e20155df01b3a1f6c0a947c4e9e4871957cff2e507939f7ea21a5fe967d84504",
      "batch_id": "BATCH-2026-006",
      "prompt_id": "OEII-STATEMENT-CODING",
      "prompt_version": "2.0",
      "notes": "Source eligibility inherited from source-BATCH-2026-005-007; human attribution and publication review pending."
    }
  ],
  "revision_history": [
    {
      "changed_at": "2026-08-16T23:17:22Z",
      "changed_by": "Murray Newlands",
      "summary": "Approved for the governed-identities pilot release under the exact scope, exclusions, rights treatment, and limitations recorded in issue #18.",
      "batch_id": "BATCH-2026-006"
    }
  ]
}

Open machine-readable record