by StyxNether

Auto-Approval: a middle permission tier for DeepSeek Harness between workspace-write and danger-full-access, auto-approving harmless commands and trusted-area targets

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions,

by Jiao-XXX

为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档，危险或不确定操作仍转人工审批。An auto-approval permission preset between workspace-write and full access for DeepSeek Harness.

by cdxiaodong

Agent security guardrail: intercepts and audits every tool call, requiring human confirmation on sensitive operations.

Semantic risk grading and progressive authorization: classifies tool calls into safe/risky/redline, asks before irreversible actions, auto-allows only approved-and-succeeded signatures.

Runtime security gate on the tool pipeline: denies calls naming hosts outside an egress allowlist, redacts credentials from results at the canonical value rather than only the rendered content, and ap