Autonomous OSS Threat Detection Via Taxonomy-Aligned LLMs

Open source software OSS ecosystems face growing threats from sophisticated supply chain attacks including typosquatting, dependency confusion, Trojan Source obfuscation, malicious build injection, and CI/CD pipeline poisoning. Existing detection approaches rely on signature-based tools and...

batch_jailbreak

批量中的安全性？理解与缓解批量提示中的安全失效 官方仓库 Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim 韩国科学技术院 KAIST 新闻 2026.09 我们的论文已被 AACL-IJCNLP 2026 Main 接收！🎉 2026.08 论文已在 arXiv 上发布！ 2026.08 代码已发布！ 概述 批量提示是一种实用的推理策略，它将多个查询打包到单次调用中。我们表明，它在效用上的成功并不 能延伸到安全性上：一个在单独提出时会被可靠拒绝的有害问题，当被嵌入到一批良性问题中时，可能会引出有害的回答。 本仓库提供了以下官方代码： ...

EUVD-2026-67846

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

Microsoft Edge for iOS Spoofing Vulnerability

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

CVE-2026-70331: Undefined Security Weakness

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

PT-2026-83265

Name of the Vulnerable Software and Affected Versions Microsoft Edge for iOS affected versions not specified Description Improper neutralization of input used for Large Language Model LLM prompting allows an unauthorized attacker to perform spoofing over a network. LLM prompting refers to the...

Improper Neutralization of Input Used for LLM Prompting

Overview strands-agents-tools is an A collection of specialized tools for Strands Agents Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the pythonrepl function in src/strandstools/pythonrepl.py. An attacker can execute arbitrary...

CVE-2026-78379 Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

EUVD-2026-65735

Improper neutralization of input used for LLM prompting in the pythonrepl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards noninteractivemode as a...

CVE-2026-78379

Amazon Strands Agents Tools (prior to 0.8.5 ) is affected by an improper input neutralization flaw in its python_repl tool. A remote attacker can craft a prompt that forwards the non_interactive_mode keyword argument through the batch tool, thereby bypassing the human consent gate and achieving a...

Improper Neutralization of Input Used for LLM Prompting

Overview strands-agents-tools is an A collection of specialized tools for Strands Agents Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the shell tool. An attacker can execute arbitrary operating system commands by crafting a prompt...

Description-Code Inconsistency in Real-World MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol MCP has emerged as a critical standard empowering Large Language Models LLMs to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool...

R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge

The misuse of Java security APIs is a serious security problem in software development. Research in 2024 has shown that this problem is widespread in LLM-generated code. However, it remains unclear whether this phenomenon persists in current models and how external security knowledge affects it...

An Empirical Evaluation of LLM-Generated Code Security across Prompting Methods

The growing use of Large Language Models LLMs for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to issues such as weak encryption and improper input validation...

Improper Neutralization of Input Used for LLM Prompting

Overview nnunet is a nnU-Net. Framework for out-of-the box biomedical image segmentation. Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting via the .github/workflows/issue-triage.yml process. An attacker can manipulate authenticated issue...

Threat Modelling Using Domain-Adapted Language Models: Empirical Evaluation and Insights

Large Language ModelsLLMs are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modelling, prior work has primarily evaluated a number of general-purpose Large Language Models under limited prompting settings. In this study, we extend th...

On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies

The security of AI-generated code remains a major obstacle to its widespread adoption. Although code generation models achieve strong performance on functional benchmarks, their outputs frequently contain bugs and security weaknesses that undermine their trustworthiness. Prior work has explored a...

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models

Large language models LLMs are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn InjectionTTI, a new multi-turn attack technique that systematically exploits stateless moderation by distributing...

CVE-2026-35655

OpenClaw before 2026.3.22 contains an identity spoofing vulnerability in ACP permission resolution that trusts conflicting tool identity hints from rawInput and metadata. Attackers can spoof tool identities through rawInput parameters to suppress dangerous-tool prompting and bypass security...

CVE-2026-35655 OpenClaw < 2026.3.22 - Identity Spoofing via rawInput Tool in ACP Permission Resolution

OpenClaw before 2026.3.22 contains an identity spoofing vulnerability in ACP permission resolution that trusts conflicting tool identity hints from rawInput and metadata. Attackers can spoof tool identities through rawInput parameters to suppress dangerous-tool prompting and bypass security...