arXiv Machine Learning June 16, 2026 By Richard J. Young, Gregory D. Moody

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

Read the original on arXiv Machine Learning →

arXiv:2605. 28734v2 Announce Type: replace-cross Abstract: A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written.

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

arXiv AI

Jun 17

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

arXiv:2510. 01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings.

By Shoumik Saha, Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Zijian Wang, Varun Kumar

llms agents multimodal benchmarks safety

arXiv AI

Jul 7

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

arXiv:2510. 15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern.

By Hanbin Hong, Shuang Wu, Shuya Feng, Nima Naderloui, Shenao Yan, Jingyu Zhang, Ali Arastehfard, Heqing Huang, Yuan Hong

llms benchmarks safety

arXiv AI

Jun 2

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

arXiv:2606. 01494v1 Announce Type: cross Abstract: Agent skills extend AI agents with reusable instructions, tools, scripts, references, and workflows, establishing a security boundary distinct from both model safety and traditional package-malware detection.

By Vincent Koc, Patrick Erichsen, Jacob Tomlinson, Agustin Rivera, Michael Appel, Nir Paz

agents safety

arXiv AI

Jul 14

Trivial Prompt Reframing Bypasses Safety Guardrails in Google\'s MedGemma-4B

arXiv:2607. 09804v1 Announce Type: cross Abstract: Open-weight medical language models are increasingly used as the base of patient-facing and clinician-support applications.

By Avi-ad Avraam Buskila

llms multimodal benchmarks safety

arXiv AI

Jun 3

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing

arXiv:2606. 02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat.

By Alexandre Cristov\~ao Maiorano

llms agents benchmarks safety

arXiv AI

Jun 6

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

arXiv:2606. 05396v1 Announce Type: cross Abstract: Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based augmentation propagates these inaccuracies because it transforms vulnerable seeds rather than synthesising vulnerabilities from a specification.

By Cristina Carleo, Pietro Liguori, Naghmeh Ivaki, Domenico Cotroneo

llms reinforcement-learning safety data-engineering

Related stories

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree

Trivial Prompt Reframing Bypasses Safety Guardrails in Google\'s MedGemma-4B

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration