unicode-security

Mojibake is a low-level Unicode library written in C11.

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.

793 confusable pairs missing from Unicode TR39, world-first cross-script dataset, font-aware SSIM scoring across 230 fonts and 22,000+ characters

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.

Audit invisible AI text watermarks and test Claude watermark claims with reproducible, local-first analysis.

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

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

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

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.

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

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.

Deterministic Unicode 17 text integrity tools for software and Agents.

'İGNORE'.lower() != 'ignore'. Turkish case-folding & Unicode confusables bypass naive prompt-injection filters 94.6% of the time — measured, with dataset + a one-line NFKC fix.