
NimBlackout
Kill AV/EDR leveraging BYOVD attack

Kill AV/EDR leveraging BYOVD attack

Benchmark for evaluating AI agent safety against attacks embedded in skill-facing context, with 155 cases across 6 risk domains, measuring task…

We asked 6 AIs about their own programming. All 6 said jailbreaking will never be fixed. Run it yourself — $2, 10 minutes.

Hands-on AI security lab platform with 50+ scenarios across prompt injection, agentic system exploitation, model manipulation, and MCP trust boundary…

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

Proof-of-concept exploit for CVE-2026-73292: CSRF attack on Semaphore UI password change endpoint, serving a malicious page that silently resets an…

Fish Live In Trees

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

Demonstrates how a malicious Python package executes arbitrary commands during pip install via setup.py, highlighting PyPI supply chain and…

Intentionally vulnerable machine learning model for hands-on security training. Explore common ML vulnerabilities, adversarial attacks, and defensive…