dsh-riskproof
Provenance-aware execution and output security for DeepSeek Harness, with visible receipts and trusted declassification.
7 results
Provenance-aware execution and output security for DeepSeek Harness, with visible receipts and trusted declassification.
SpecWave — multi-host coding CLI (Cursor / Claude Code / DSH / agents) + P0 gates & Harness process track. Spec-driven discipline: mechanical gates (exit 2), S2 audit trail, hat roles. Formerly SpecGate / dsh-coding-kit. npx spec-wave
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
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。
Self-evolving memory for DeepSeek Harness (DSH): earned experiences, diary/fact semantic memory, concern tracking, and an append-only audit ledger.
Agent observability plugin for DSH — behavior audit, cost tracking, anomaly detection