
anamnesis-release
Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…
ai-securitybinary-exploitationeducation+9
633

Evaluation framework for studying LLM agents that automatically generate working exploits from vulnerability reports, bypassing modern security…

AI runtime inventory: discover shadow AI, trace LLM calls

Semantic graph-based version control for AI-written code. Tracks entities and relations instead of file diffs, enabling blast radius analysis, shadow…

Windows network reconnaissance scanner with ping sweeps, TCP port scanning, and deep AI/ML service detection for finding shadow AI, rogue LLM…

Defensive framework that maintains a safety-focused shadow memory to detect and block prompt-injection and long-horizon threats against LLM agents…