
ghostsplice
Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

Ghostsplice repository: PoC for Cross-Channel Trust Fragmentation Attack

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

Scan LLM outputs and AI-generated content for data exfiltration signals (EchoLeak, CVE-2025-32711) before they reach users or downstream systems

AI-powered threat intelligence platform for automated CVE/ransomware monitoring, domain surveillance, data leak detection, and incident response with…

Open-source AI agent firewall that scans HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, emitting verifiable…

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

Embed multiple secret messages in LLM chat token choices using arithmetic/Discop steganographic coders, with bit-exact decoding and steganalysis…

Automating Host Exploitation with AI

Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply chain attacks, test prompt injection…

A transparent PII redaction proxy for LLM API traffic. Sits between an application and an LLM provider (currently Anthropic), pseudonymizing…

AI Prompt Secret Scanner: local proxy and Claude Code hook that blocks secrets before they reach AI APIs

Deterministic memory-poisoning / prompt-injection measurement axis — CoSnitch (CVE-2026-24301) anchored. Inspect scorer, signed receipts.…

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data…

Sigma detection rules for AI agent security monitoring

A Proof-of-concept repository showing how an untrusted MCP server can steal literally everything...

A small Rust CLI that strips secrets from your clipboard on demand.

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…

AISec Plus Week 1 threat write-up — EchoLeak (CVE-2025-32711), zero-click indirect prompt injection in Microsoft 365 Copilot.