dsh-llmasking
Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.
10 results
Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.
Export-copy redaction for DeepSeek Harness session telemetry
Privacy-minimal provenance receipts for DeepSeek Harness workspace instructions
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
Non-intrusive safety belt for DeepSeek Harness: blocks API keys pasted to the agent, blocks secret writes, tracks leak events, and offers a workspace health scan. 非侵入式安全护栏:拦截粘贴给 Agent 的 API 密钥、写入拦截、泄露追踪与工作区安全体检。
Turn DeepSeek Harness sessions into redacted, README-ready animated demos — as a local CLI or DSH plugin.
保险区 Vault Wall — 让 DeepSeek Harness 无法感知、无法触碰用户指定敏感路径的隔离墙插件(隔离墙 + 临时借出 + 触碰审计 + 紧急熔断)
Structured, machine-readable CI output for DeepSeek Harness (dsh): session event capture with JSON/NDJSON reports, JUnit XML, semantic exit codes, artifact collection and privacy redaction. Ships as a dsh profile bundle and a standalone CLI.
DSH plugin: anonymize workspace-external file paths before model requests with user confirmation
文本脱敏:把文本中的邮箱/手机号/身份证/银行卡/IP/密钥等敏感信息替换为掩码,分享前保护隐私