
LeakGauge
Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

A static + runtime security scanner for MCP (Model Context Protocol) servers

FastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)

PoC for CVE-2025-62593: unauthenticated RCE in Ray (CISA KEV). Stdlib-only Python.

Defensive engagement & threat intelligence research laboratory. Converts inbound scam emails into actionable IOCs through controlled, policy-driven…

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

Study of CVE-2018-6341 in React, demonstrating AI-assisted vulnerability detection, root-cause analysis, and remediation guidance for JavaScript…

Live recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.

Local white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…

CVE-2026-73678 — MindsDB Minds Platform unauthenticated RCE via scratchpad exec (CVSS 10.0). Verified end-to-end with real LLM

OpenMed < 1.5.2 unauthenticated RCE via PII privacy-filter model loading and trust_remote_code=True

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

Strip multi-vendor AI provenance marks: Unicode text hygiene, statistical rewrite hooks, and C2PA/metadata from PNG/JPEG/SVG/PDF/DOCX/HTML/MD

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

AISA-Scanner is an AI-powered autonomous vulnerability scanner that maps CVEs to metasploit exploits, MITRE, CEH, and SANS, delivering intelligent,…

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…

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