www-project-top-10-for-large-language-model-applications

www-project-top-10-for-large-language-model-applications OWASP Foundation Web Repository OWASP Top 10 for Large Language Model Applications Welcome to the official repository for the OWASP Top 10 for Large Language Model Applications! About This Repository This repository contains the OWASP Top 1...

kong

Kong: The Agentic Reverse Engineer LLM orchestration for reverse engineering binaries What is Kong? Most tasks follow a linear relationship: the more difficult a task, the longer it usually takes. Reverse engineering and binary analysis is a task in which the actual difficulty is somewhat trivial...

inspect_petri

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

oss-fuzz-gen

A Framework for Fuzz Target Generation and Evaluation This framework generates fuzz targets for real-world C/C++/Java/Python projects with various Large Language Models LLM and benchmarks them via the OSS-Fuzz platform. More details available in AI-Powered Fuzzing: Breaking the Bug Hunting Barrie...

aegis-audio-defense

AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks Submitted to ICASSP 2027. AEGIS keeps the target audio-language model frozen and adds a mid-layer risk gate that conditionally drives late-layer safety adapters, with closed-loop scaling at...

markdown-exfil-tester

valtik-markdown-exfil-tester Black-box tester for indirect prompt injection leading to markdown / HTML exfiltration in LLM-backed chatbots. This is the vulnerability class that hit Microsoft 365 Copilot CVE-2025-32711, aka EchoLeak, ChatGPT OpenAI Feb 2026 patch, and Salesforce ForcedLeak. The...

deleting-the-trace

Control-token injection attacks on tool-using agents Code and logged measurements for a study of two input-level attacks on tool-using language model agents. The first attack appends a short string of a model's own channel-control tokens to untrusted input; the tokenizer reads it as an...

EntropicaPublic

March updates I need to move some work over from the private repos. The exploration into using massivly multheaded models with mixer and readout functions separated continues. Currently training up a Chinese TinyStories on a 3B-equivalent model that trains, easily, on an 8GB gpu. We're looking at...

batch_jailbreak

Official Repo for Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting Kihyun Kim, Hee-Seon Kim, Wonjun Lee, Changick Kim Korea Advanced Institute of Science and Technology KAIST News 2026.09 Our paper has been accepted to AACL-IJCNLP 2026 Main! 🎉 2026.08 Paper is...

birdy-edwards

BIRDY-EDWARDS 2.0 Infiltrate & Expose Automated AI powered Facebook intelligence tool for target profiling, network analysis and threat reporting. Runs entirely on-device via Ollama. AI-powered Facebook SOCMINT platform — 100% local, zero cloud dependency. For lite version check this repo click...

CVE-2026-54559

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

CVE-2026-54559 PocketSphinx: Buffer overflows in language and acoustic model loading code

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

CVE-2026-54559

PocketSphinx (a lightweight speech recognizer, including its Python bindings) versions 5prealpha through 5.1.0 are affected by buffer overflow vulnerabilities in its model-loading code. The trie language-model loaders in src/lm/ngram_model_trie.c fail to validate boundary conditions in ARPA, DMP,...

CVE-2026-54559 PocketSphinx: Buffer overflows in language and acoustic model loading code

PocketSphinx is a small speech recognizer. Prior to 5.1.1, the trie language-model loaders in src/lm/ngrammodeltrie.c do not adequately validate boundary conditions in ARPA, DMP, and binary format headers, and the acoustic-model loaders in src/mdef.c and src/util/bio.c use sscanf with unbounded...

EEF-CVE-2026-78230 AshAi aggregate tool can read field-policy-protected fields

Summary AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type min, max, sum, avg that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records replacing...

EUVD-2026-72924

AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type min, max, sum, avg that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records replacing them with...

Using LLMs to Elicit Security Requirements for Service-Oriented Cyber Ranges

Cyber ranges are complex environments comprising many interacting components and stakeholders with different security concerns. The Service-Oriented Cyber Range SOR is no exception, particularly when it comes to training scenarios targeting critical infrastructure. Security concerns are translate...

PT-2026-81211

U-Boot before 2026.10-rc5 contains a use-after-free vulnerability in the httpc recv cb function within the lwIP wget implementation. When HTTP data storage fails, the callback frees the connection PCB but returns ERR BUF instead of ERR ABRT, causing the TCP input path to access released memory an...

CVE-2026-72742

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...

EUVD-2026-56886

DSPy 3.3.0b1 contains a file exfiltration vulnerability in the Image and Audio output field adapters that allows attackers with influence over language model outputs to read arbitrary local files by injecting a filesystem path into the url field of a parsed Image or Audio typed output. The...