ai-safety 6
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent decides allow/deny on the approval answerer chain, with fail-closed fallback and full session-log audit.
dsh plugin add dsh-auto-reviewRule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.
dsh plugin add dsh-approve-for-meIndependent Codex Guardian-style approval reviewer for DSH.
dsh plugin add dsh-guardian-approvalDSH permission-gate for the DeepSeek Harness 0.1.5 line: a single self-sufficient, deterministic-first, fail-closed gate covering P0 hard-deny -> P1 session grant -> P2 static rule (allow/deny) chain -> P3 optional LLM semantic classifier -> P4 ask, with
dsh plugin add dsh-perm-gateDeepSeek Harness plugin: Jev-backed guardrails for prompts, tool calls, tool results, and model responses.
dsh plugin add @codebam/dsh-jev-guardrailsRuntime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.
dsh plugin add dsh-ccs-security