
trustmebro
Bypass llm guardrails by confusing it with fabricated tool output.

Bypass llm guardrails by confusing it with fabricated tool output.

MAAD Attack Framework - An attack tool for simple, fast & effective security testing of M365 & Entra ID (Azure AD).

A font-based deception tool for red teaming, security research, and whatever else.

Playing around with Stratus Red Team (Cloud Attack simulation tool) and SumoLogic

A tool to find folders excluded from AV real-time scanning using a time oracle

Security benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

Adversarial image perturbation tool that uses SAM segmentation and CLIP models to evade AI-based scam image classifiers for security research.

C++ tool using libtins to craft and broadcast DHCP requests with random MACs across an IP pool, exhausting DHCP leases to demonstrate DHCP starvation…

CVE-2026-54121 (Certighost) AD CS DC-impersonation PoC. Patched SAN handling + MAQ-safe account reuse.

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

image scaling attacks for multi-modal prompt injection

C# obfuscator that bypass windows defender

Leverage a legitimate WFP callout driver to prevent EDR agents from sending telemetry

Generate Linux executables that simulate adversary behaviors and techniques for testing detection and response coverage. Consumes JSON for easy…

Tools and PoCs for Windows syscall investigation.

Abuses Windows Filtering Platform to launch a console as NT AUTHORITY\SYSTEM or impersonate another logged-on user for privilege escalation during…