The paper empirically evaluates the security quality of LLM-generated code across various prompting methods, finding that while prompting alters the structure of weaknesses, it is insufficient to reli…

The paper introduces a validated, consensus-labeled prompt bank that separates requests for executable malicious code (weapons) from requests for general harmful security knowledge, providing a more g…

The paper introduces the Mitigation-Aware Chain-of-Thought (MA-CoT) framework, which significantly enhances the security reliability of code generated by LLMs across multiple languages and models.

The paper proposes an automated, standardized framework to empirically compare the security quality of code generated through human-only, LLM-only, and hybrid collaboration methods.

The paper tested the hypothesis that wrapping untrusted prompt inputs in mock tool calls would improve LLM robustness, but found that this technique generally fails and can even increase vulnerability…

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

This paper introduces UPAttack, a novel threat model demonstrating that focusing on explicit usability requirements can cause LLMs to generate insecure code by neglecting implicit security constraints…

The paper introduces False Security Confidence (FSC), a new metric to measure the inherent prevalence of security vulnerabilities in code generated by LLMs that are otherwise functionally correct, eve…

The paper introduces a large, consensus-labeled prompt bank that reliably distinguishes between requests for executable malicious code and requests for harmful security knowledge, providing a standard…

The paper evaluates multi-LLM strategies for secure code generation, finding that hybrid pipelines combining ensembling, static analysis, and patching achieve the strongest security performance, outpe…

The paper analyzes GitHub security advisories for LLM-integrated open-source systems, finding that while most vulnerabilities map to existing code-level weaknesses, the architectural risks like Supply…

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

QASecClaw, a multi-agent LLM system, significantly improves the accuracy of Static Application Security Testing (SAST) by using specialized LLM agents to filter out false positives, achieving an F1 sc…

The paper introduces a novel, large-scale dataset of vulnerable code snippets linked to CAPEC and CWE, generated using advanced LLMs, to improve automatic vulnerability detection.

The paper introduces TRAILS~, a novel method that improves code correctness validation by grounding LLM reasoning in concrete (input, output) pairs derived from specifications, achieving state-of-the-…

This paper identifies the 'Format-Reliability Gap'—where LLMs know about code vulnerabilities but generate insecure code anyway—and proposes a localized, per-vulnerability steering vector fix that sig…

This survey provides a comprehensive, practical guide to ensuring the trustworthiness of complex, autonomous agentic AI systems by focusing on safety, robustness, privacy, and system security.

The paper introduces SKILLSCOPE, a system that detects security-relevant behaviors in code-backed LLM skills that are not disclosed in the natural language description, finding that 9.4% of skills exh…

The paper introduces LCC-LLM, a code-centric framework and dataset that significantly improves the reliability of malware attribution and static analysis by grounding LLM reasoning in comprehensive, m…

This paper systematically reviews thirteen diverse malicious-code prompt corpora used to evaluate LLM refusal, identifying critical methodological gaps in current research.