
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,…

Bypass llm guardrails by confusing it with fabricated tool output.

Protection against Model Serialization Attacks

A security scanner for your LLM agentic workflows

:cloud: :zap: Granular, Actionable Adversary Emulation for the Cloud

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

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

🐢 Open-Source Evaluation & Testing library for LLM Agents

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…

Hardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).

Self-Defeating Audits: reproducible lab showing a low-privilege PostgreSQL role reversibly blinding a trigger-based auditor + poisoning attribution…

A curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation

A curated collection of resources for learning and researching LLM prompt injection attacks, defenses, and security.

PoC funcional de CVE-2026-17106 (CopyEscape): carrera TOCTOU en docker cp que permite escritura arbitraria en el host Docker. Laboratorio Docker +…

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

PoC repository for the blog post CopyEscape: Taking Over Docker Hosts with docker cp

CVE-2026-20685 - Draft or TODO