arXiv:2610.28802v1 Announce Type: new Abstract: How much does an agent harness affect vulnerability discovery, and does its value depend on the model? We study 24 model-runner configurations using an open-source harness on a production codebase whose vulnerabilities were non-public at scan time. The pipeline combines static screening, LLM investigation, model self-revalidation, root-cause mapping, independent source review, and isolated proof-of-concept confirmation.
How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery
About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.28802
Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
Hacking on Autopilot: Inside ARTEX Cybercrime Campaigns
Key Points Agentic hacking platforms like ARTEX, where AI models autonomously drive vulnerability discovery and exploitation, have been observed to be used by various…
A Hybrid Approach for Automated Security Pattern Recovery
arXiv:2611.05823v1 Announce Type: new Abstract: Security-by-design emphasises integrating security into software design and development. Security pattern catalogues…
Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents
arXiv:2611.00138v1 Announce Type: new Abstract: Existing large language model (LLM) backdoor attacks operate primarily in chat settings, where the risk is bounded by…
CyberStrikeAI in the wild: the use of AI in real-world attacks on organizations
Introduction As part of proactive threat monitoring, Kaspersky’s Cyber Threat Intelligence team identified a malicious campaign involving C2 agents controlled by…
ARTEX and Friends: Enter Agentic Offensive Frameworks
Written by: Aurora Blum, David Mainor, Rohit Nambiar, Omar ElAhdan, Matthew McWhirt, Will Silverstone, Bhavesh Dhake, Chris Busse Introduction Recent intrusions in which…
When Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills
arXiv:2610.37734v1 Announce Type: new Abstract: Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in…