{"slug":"clawhub-guangfuwu-privora-cn-quant","facts":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/guangfuwu/skills/privora-cn-quant","sourceUrl":"https://clawhub.ai/guangfuwu/skills/privora-cn-quant","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T06:16:00.576Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-guangfuwu-privora-cn-quant/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guangfuwu-privora-cn-quant/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T06:16:00.576Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"4K downloads","href":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceUrl":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T06:16:00.576Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.0.57","href":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceUrl":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceType":"release","confidence":"medium","observedAt":"2026-09-21T09:28:02.096Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-guangfuwu-privora-cn-quant/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-guangfuwu-privora-cn-quant/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"changeEvents":[{"eventType":"release","title":"Release 1.0.57","description":"## v1.0.57 · 2026-09-18 Host-consent MCP tool annotations + honesty pass on the confirm-handshake wording (#1462 ① route — ClawHub had flagged v1.0.56 `suspicious` for \"agent can complete destructive workflow/scheduler operations without independent human approval\"). - **MCP server (`mcp-server/`) now discloses a risk signal to the host it never gave it before.** Every tool in `tools/list` carries an `annotations` object (`readOnlyHint:true` on the 10 read-only tools; `destructiveHint:true` on the new dispatcher below). A new tool, `execute_confirm_required_skill`, is restricted — via a live per-call catalog lookup, never a static list — to the ~20 `confirmRequired:true` skills (the same destructive/high-risk set this package's own two-step approval handshake already gates); `execute_skill` now refuses those skillIds client-side and points the caller at the new tool instead. **These annotations are a disclosure, not a security boundary** — a host is free to ignore them, exactly like this package's own packaging-time skill allowlist; the actual, unbypassable authorization check has always been and remains the server-side scope check. `mcp-server`'s `tools/list` is now 12 tools, not 11 — see `mcp-server/README.md` and `mcp-server/CHANGELOG.md` (`0.1.2`). - **Corrected an over-strong claim in a live, machine-readable API field, not just prose**: the token-mode 409's `next` field used to read `'human-approves-then-resend-see-nextAction'`. It does not — `AgentApprovalService. selfConfirm()` sets `approver_user` to the SAME identity as the requester; the two-step handshake this package documents can be, and normally is, completed by the same agent that triggered it. Now reads `'self-confirm-or-await-admin-then-resend'`. The §高风险操作确认握手 409 example in this file is updated to match. - **《🛡️ Scope 与操作者责任》一节补上同一句逐字遵从的魔鬼在细节里：**“平台强制两步确认握手” 指的是“强制两步”，不是“强制两个主体”——补上一句明确说明：这道门防的是单次误触，不是 他人审批；要真正的人工把关，只有两条路：不授予这些 scope，或走平台 UI 由管理员 approve/reject。 - 无行为变化：本包自己的 REST/shell 调用链路不受影响，上述两条都是 MCP 新增能力 + 文档误差修正。","href":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceUrl":"https://clawhub.ai/guangfuwu/privora-cn-quant","sourceType":"release","confidence":"medium","observedAt":"2026-09-21T09:28:02.096Z","isPublic":true}]}