.claude/skills/<skill-name>1 structural issue
- error: The fixed release did not provide readable SKILL.md content.
SKILL.md
Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Privora · AI Agent 投资工作流平台 — Bearer Token 即接入 /agent/skills/execute 通用 dispatcher,覆盖 A 股/港股/美股/黄金/基金/财报数据 + Python 回测(含 sandbox)+ 模拟交易 + 组合归因(α/β TWR)+ 云端告警 + 流程编排。Hermes / Claude / GPT / OpenClaw 全兼容。
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/<skill-name>SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/<skill-name>SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/<skill-name>SKILL.mdRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @guangfuwu/privora-cn-quantclawhub inspect @guangfuwu/privora-cn-quant --version 1.0.57This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
content unavailableThis is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:540fe1cd550c7675bec688d61b628db01374cbebe5246e4846a07e30b5086d47scripts/lg_agent_exec.shscripts/lg_agent_list.shskill-card.mdSKILL.md## 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 ann…
Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.
These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.
sha256:a33e90625b69a945245eb5f3411d965f37a4ea5d884659a4f75e235317e2dce3sha256:5ac500bd0367e7fcf810810186d77c1a0da4c36679b8b6916ea5ac31d9c33768sha256:64e35e1797b23b4124896b9acaa4dc3ae8ef2fbf9dbbbe58ad94722dbf6be972sha256:49a16397a038cb8c6b331a8a1d86c441d7e4a000e00ce19e84f086b6cedd275a