arXiv AI July 22, 2026 By Yohann Sidot

They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pipeline Into an Attack Surface

arXiv:2607. 19267v1 Announce Type: cross Abstract: We study a five-agent CI/CD pipeline (triage -> developer -> security-scan -> review -> approve/deploy), built from five distinct production LLMs across three providers, behind an LLM firewall in shadow mode.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 23

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.

By Aarushi Singh

llms agents benchmarks safety

arXiv AI

Jun 9

SecureClaw: Clawing Back Control of LLM Agents

arXiv:2606. 09549v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any final output check can intervene.

By Yuhan Ma, Stefan Schmid

llms agents multimodal

arXiv AI

Jul 13

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

arXiv:2602. 20064v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results.

By Zac Garby, Andrew D. Gordon, David Sands

llms agents benchmarks

arXiv AI

Jul 29

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.

By Genliang Zhu (Accentrust, Georgia Institute of Technology), Chu Wang (Accentrust, University of Illinois Urbana-Champaign)

agents safety

arXiv AI

Jul 8

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

arXiv:2607. 05743v1 Announce Type: cross Abstract: AI coding agents now read repositories, call tools, and execute shell commands with limited human oversight, and a fast-growing body of work studies whether the execution layer around them is actually safe.

By Mohammadreza Rashidi

llms agents benchmarks safety

arXiv AI

Jun 2

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say

arXiv:2606. 00152v1 Announce Type: cross Abstract: LLM-based agents are rapidly advancing, autonomously invoking external tools to complete multi-step tasks for users.

By Mingxuan Zhang, Jiahui Han, Dadi Guo, Songze Li, Guanchu Wang, Na Zou, Dongrui Liu, Xia Hu

llms agents benchmarks safety

Related stories

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

SecureClaw: Clawing Back Control of LLM Agents

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say