
Prompt-Injection-in-the-Wild
Tracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…

Tracker of publicly reported prompt-injection techniques, broken down by delivery method, encoding, and propagation behavior, with confirmed models,…

Security scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment

GitLab Duo DevSecOps loop where a second AI re-attacks every AI-written fix, saving each successful bypass as a permanent antibody replayed in CI and…

Protection against Model Serialization Attacks

Clusters and elements to attach to MISP events or attributes (like threat actors)

Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…

Anti-LLM obfuscation via finger counting