yolorouter/dsh-llmasking

yolorouter★ 0TypeScriptLast synced: 2026-08-16

Open on GitHub

Transport-layer data masking for deepseek-harness (dsh): the model sees placeholders, you see real values restored live in the stream.

README excerpt

dsh-llmasking 🌐 English · 简体中文 Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process on their way to the model — while your session log, UI, and tool executions keep seeing real values, restored live in the stream. The threat model is logs keep truth, the wire carries masks : your dsh session log, terminal UI, and every tool execution see real values; only what crosses the network to the LLM provider is masked. Session titles and compaction summaries are covered too — they ride the same llm/stream seam. Powered by the llmasking engine: universal detectors (email, bank card with Luhn check, IP, URL, international phone, secret family: cloud keys / PEM / JWT / git tokens / high-entropy passwords), CN rules (mobile, ID card with ISO 7064 check, landline), US rules (SSN, phone), plus your own keywords. Same value → same placeholder within a session; secrets are redacted one-way ( [SECRET 1] never maps back). Quick start 1. Install dsh (skip if you already run it — needs Node ≥ 22, dsh ≥ 0.1.0-rc.6 ): 2. Install the plugin into a profile. Pick any profile name — dsh initializes it with dsh-base on first use: 3. Boot it: 4. Configure a model. …

View full README on GitHub →
Skins / UIdeepseek-harnessdsh-pluginpii-maskingprivacyskin

Category