
Guardrails
Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

Programmable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…

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

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

Header-only Windows x64 indirect syscall library. Zero CRT, zero IAT, VEH anti-BP, AMSI/ETW bypass, W^X memory, per-call dynamic stubs.

Lightweight native Windows memory scanner for AV/EDR platforms, detecting suspicious mapped images and manual DLL injection techniques by IAT thunk

Obfuscate specific windows apis with different apis

Browser extension that detects PII and sensitive data in AI chats, masks it with placeholders before sending, and restores originals in replies—all…

Defensive Linux firewall toolkit combining IPTables rules and kernel configuration to protect hosts and servers against DoS, DDoS, and network…

Dynamic Windows API resolver and unhooker that detects and restores hooked functions (IAT, EAT, inline patches) to invoke unmonitored system calls…

Offline heuristic analyzer that scores suspicious SMS, chat messages and links for scam and phishing indicators, explaining each warning sign with…