Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries to embed instructions directly in web resources, i.e.,...

Beyond Code Reasoning: A Specification-Anchored Audit Framework for Expert-Augmented Security Verification

Security-critical software is routinely audited by tools that reason about vulnerabilities as repository-local code patterns. Yet specification-governed systems -- protocol stacks, consensus implementations, cryptographic libraries -- are constrained by invariants and correctness conditions defin...

ExploitSense

ExploitSense ExploitSense is a local-first vulnerability anal...

Malicious code in wm-plugin-teach-me-widget (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector a8892d058e7f10e304a86eea230ef7fa8fbf9a76da1d09b60f5498305690d4bc The package wm-plugin-teach-me-widget was found to contain malicious code. Source: ghsa-malware...

OpenSOC-AI: Democratizing Security Operations with Parameter Efficient LLM Log Analysis

Small and medium sized businesses SMBs face an escalating cybersecurity threat landscape, yet most lack the resources to staff full Security Operations Centers SOCs or deploy enterprise grade detection platforms. This paper presents OpenSOC-AI, a lightweight log analysis framework that uses...

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code

Developers and organizations are using Large Language Models LLMs to generate security-critical code more frequently than ever, including cryptographic solutions for their products. This study presents an empirical evaluation of cryptographic security in 240 Rust code samples for two crypto...

EDySec: A Deep Learning-Based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem

The security of open-source software repositories is increasingly threatened by next-gen software supply chain attacks. These attacks include multiphase malware execution, remote access activation, and dynamic payload generation. Traditional Machine Learning ML detectors struggle to detect these...

MAL-2026-3123 Malicious code in apple-app-store-server-library-poc (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7f6b57befbd248b884d81978566bd3d4a57ef499f1eb8f8f66c00dc02e76588c The package apple-app-store-server-library-poc was found to contain malicious code. Source: ghsa-malware...

MAL-2026-3103 Malicious code in amzn_codewhisperer_streaming_client (crates.io)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis 7fc27be867bc1ae651b345d2f825d0ac8d796615c022747306e87bd3ff0d1fc8 The OpenSSF Package Analysis project identified 'amzn-codewhisperer-streaming-client' @ 99.0.1 crates.io as malicious. It is considered maliciou...

MAL-2026-3120 Malicious code in @pyme-web/web-api (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector e52ac4b8d97b81cff5824f4ddc38897183df4e20ecd3f1e7df62e8f6645f236a The package @pyme-web/web-api was found to contain malicious code. Source: ghsa-malware...

Malicious code in @pyme-web/ui-base (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6780882125fbf59796027cea605339595d23058e19a6a2a257637f225adb51e8 The package @pyme-web/ui-base was found to contain malicious code. Source: ghsa-malware...

Malicious code in semantic_search_client (crates.io)

--- -= Per source details. Do not edit below this line.=- Source: ossf-package-analysis 2495e4537e60cafc5bc13f96987b82749fce367078ee036e3e4fb4421b5bdf4c The OpenSSF Package Analysis project identified 'semantic-search-client' @ 99.0.1 crates.io as malicious. It is considered malicious because: -...

Malicious code in @apple-pay-trust/authorize-payment (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f6403670e0f9573b88d997609a27ef3630ca5d0442446368011a1980a1b56298 The package @apple-pay-trust/authorize-payment was found to contain malicious code. Source: ghsa-malware...

MAL-2026-3111 Malicious code in @apple-pay-trust/authorize-payment (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f6403670e0f9573b88d997609a27ef3630ca5d0442446368011a1980a1b56298 The package @apple-pay-trust/authorize-payment was found to contain malicious code. Source: ghsa-malware...

MAL-2026-3117 Malicious code in @business_promocode/cancel_promocode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 002798d60b98859a68bc9daf0ebaf7794b8d83973b69fb4c8bfe9979f685e51d The package @businesspromocode/cancelpromocode was found to contain malicious code. Source: ghsa-malware...

Malicious code in @activation_code/activate (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 051c685a7704a23fd8a744185c9b8551c7acda63ebf95feabd3ca4b9e1f8ede6 The package @activationcode/activate was found to contain malicious code. Source: ghsa-malware...

MAL-2026-3116 Malicious code in @business_promocode/apply_promocode (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 5adac459fd1c8fca06e818942c9a98e6f798828163fadd996266ae7660132ae7 The package @businesspromocode/applypromocode was found to contain malicious code. Source: ghsa-malware...

Malicious code in @b2b_blocker/show_activation_error (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 79dc8a9f5dac0334c50b1129f725d9f0c98e7c1085624d74c6172ade69db8417 The package @b2bblocker/showactivationerror was found to contain malicious code. Source: ghsa-malware...

Malicious code in @activation_code/error (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector fec73b17468bf333bb1bf6a071209103b774e371dfbf9961ad522dbd006fff7d The package @activationcode/error was found to contain malicious code. Source: ghsa-malware...

Malicious code in @apple-pay-trust/finish (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 9abd2d210c4a5df0e95f326e80b2e6618647c03ba4158e1d6ffbd36d9f7b800a The package @apple-pay-trust/finish was found to contain malicious code. Source: ghsa-malware...