VulnFanatic-NG

VulnFanatic-NG Investigación de vulnerabilidades asistida por LLM para Binary Ninja. VulnFanatic-NG añade un panel lateral que escanea el binario actual y pregunta a un LLM — un modelo alojado localmente compatible con OpenAI por defecto, o Anthropic Claude, Google Gemini, o Azure OpenAI ver...

Investigating Detection and Obfuscation of Prompt Injection Attacks against Software Reverse Engineering AI Agents

Agentic software reverse engineering systems are vulnerable to prompt injection attacks placed into the source code of executable binary files. This research demonstrates defensive tactics for detecting the presences of prompt injection strings in the decompiler output of adversarial example...

ndaybench

ndaybench A benchmark for measuring whether AI agents can bui...