Mojibake is a small, fast, self-contained Unicode library written in C11.

c emoji unicode internationalization cross-platform cpp utf-8 webassembly character-encoding zero-dependency text-processing text-segmentation utf-16 case-folding unicode-normalization unicode-library unicode-collation grapheme-clusters bidirectional-text unicode-security

• Updated Nov 12, 2026
• C

AI-detector auditing toolkit: measures how often a detector flags genuine human writing, how stable its verdict is across seeds, and whether that verdict survives meaning-preserving edits. Detector-in-the-loop measurement harness. Claude Code skill + Python CLI. MIT.

python nlp open-source benchmark reproducible-research model-evaluation turnitin false-positives gptzero ai-detection zerogpt writing-tools ai-detector claude-code robustness-testing claude-code-skill unicode-security detector-evaluation

• Updated Oct 22, 2026
• Python

The world's first font-by-font confusables dataset: which Unicode characters look alike, measured from the outlines of 322 fonts at the size people read them. CC BY, used in Mozilla's add-on name checks.

unicode fonts dataset homoglyph anti-spoofing tr39 confusables visual-similarity idn-homograph font-security unicode-security

• Updated Sep 29, 2026
• TypeScript

Strip invisible Unicode (U+200B zero-width space, U+00A0 NBSP, curly quotes) from clipboard text. 从复制粘贴里筛掉隐形字符，解决飞书/网页/AI聊天复制代码报 stray '\342'、IndentationError、VLOOKUP 匹配不上的问题

windows rust cli unicode clipboard paste developer-tools text-processing clipboard-manager lark copy-paste zero-width-space sanitizer nbsp text-cleaner zero-width feishu invisible-characters unicode-security

• Updated Oct 18, 2026
• Rust

Research-only AI watermark & provenance robustness toolkit: local reverse proxy (OpenAI/Anthropic/Gemini) + CLI stripping C2PA/EXIF/XMP, zero-width & homoglyph Unicode, KGW text watermarks, DWT/Tree-Ring image stego, AudioSeal, PDF/DOCX/PPTX/XLSX metadata, and Trojan Source (CVE-2021-42574) code scanning.

python privacy reverse-proxy provenance exif steganography digital-forensics watermarking adversarial-machine-learning security-research homoglyph watermark-removal c2pa llm metadata-removal content-credentials synthid trojan-source unicode-security ai-watermarking

• Updated Aug 16, 2026
• Python

A specialized tool that generates highly obfuscated BIP custom derivation paths and passphrases. It uses layered noise (emojis, multi-script characters, and controlled entropy) to create an additional hidden (plausible deniability) protection layer in case a mnemonic seed is exposed

unicode cryptography entropy python3 cryptocurrency passphrase termux fuzzer emojis passphrase-generator hd-wallet bip39 bip32 normalization security-tools unicode-normalization nondeterministic derivation-path unicode-security

• Updated Nov 7, 2026
• Python

🛡️ Zero-dependency invisible prompt injection & ASCII smuggling firewall for LLMs, RAG & AI Agents. Detect, decode, and neutralize hidden Unicode payloads.

typescript steganography zero-dependency prompt-injection llm-security owasp-llm ascii-smuggling ai-agent-security rag-security unicode-security

• Updated Nov 4, 2026
• TypeScript

Zero-dependency heuristic scanner for prompt-injection indicators in untrusted text, for the boundary of LLM agent pipelines.

python security zero-dependency ai-safety ai-agents prompt-injection llm-security unicode-security

• Updated Aug 24, 2026
• Python

Unicode Spoof and Homoglyph Detection for MoonBit (UTS #39)

github-pages unicode hackathon webassembly unicode-normalization homoglyph confusables spoof-detection moonbit unicode-security uts39

• Updated Oct 30, 2026
• MoonBit

Unicode Homoglyph Detector — Offensive Unicode Security Analysis

python security unicode python3 punycode idna idn homoglyph phishing-detection confusables unicode-security

• Updated Sep 30, 2026
• Python

Detect and neutralize Unicode concealment codepoints in MCP tool metadata (covert-channel control). AGPL-3.0-or-later.

python mcp security-tools prompt-injection llm-security model-context-protocol agent-security unicode-security

• Updated Sep 5, 2026
• Python

SMUGGLR is a browser-based Unicode steganography and text obfuscation toolkit for experimenting with invisible characters, homoglyphs, whitespace ciphers, and Unicode-based payload hiding techniques — all fully client-side with zero network calls. 🔓

cybersecurity steganography web-security zero-dependency offensive-security red-team data-hiding social-engineering security-research client-side-security browser-security invisible-characters payload-obfuscation zero-width-characters text-obfuscation unicode-security unicode-steganography homoglyph-attacks whitespace-ciphers encoding-exploitation

• Updated May 13, 2026
• HTML

Reveal and remove hidden Unicode such as zero-width spaces, look-alike whitespace, and bidi controls. Runs locally.

chrome-extension unicode chrome privacy text-cleaner zero-width ai-text manifest-v3 unicode-security

• Updated Oct 25, 2026
• JavaScript

Detect, decode and remove hidden Unicode: invisible text, ASCII smuggling, homoglyphs, Trojan Source bidi and prompt injection. Python library, CLI and GitHub Action for LLM, code and AI agent security.

python sanitization security unicode mcp steganography punycode sarif homograph-attack ai-security homoglyph zero-width github-actions confusables invisible-characters prompt-injection llm-security ascii-smuggling trojan-source unicode-security

• Updated Nov 10, 2026
• Python

Audit whether an AI tool approval view faithfully represents its raw payload.

ai-safety ai-agents mcp-security unicode-security approval-ui

• Updated Aug 24, 2026
• JavaScript

Deterministic offline scanner for repositories and package artifacts, detecting prompt injection, refusal bait, Trojan Source, obfuscation, and supply-chain anti-analysis before AI code review.

go cli golang security obfuscation ci static-analysis software-supply-chain sarif security-tools devsecops code-scanning sast ai-security supply-chain-security prompt-injection llm-security trojan-source unicode-security offline-scanner

• Updated Jun 18, 2026
• Go

Breaks the hex before your AI agent falls for it: scans agent skills, MCP servers and tools for hidden, disguised and poisoned instructions, and guards tool calls and chat at run time. Browser, CLI, GitHub Action.

mcp sarif ai-security github-action prompt-injection llm-security agent-skills unicode-security

• Updated Nov 10, 2026
• Python

Validated but not canonical: how URL, e-mail and hostname validators in seven ecosystems handle invisible characters, confusables and IDNA edge cases

email-validation url-parsing idna security-research unicode-security parser-differential

• Updated Nov 9, 2026
• Python

Phishing-domain detection from Certificate Transparency logs, with a measured false-positive rate. Deterministic: UTS#39 homoglyph skeletons, weighted edit distance, combosquat segmentation. No ML.

python certificate-transparency typosquatting blue-team threat-detection homoglyph phishing-detection unicode-security

• Updated Sep 7, 2026
• Python

Layered detection of lookalike senders and support-team / recruiter impersonation for messaging platforms, with a brand-parametric adversarial benchmark. Python, PyPI.

python phishing impersonation llm-security lookalike-domains unicode-security

• Updated Oct 30, 2026
• Python