Real Skill packageSource verifiedClawHub registry

Privora · 实时监控 · 黄金实时监控 / 基金净值监控 / 股价预警 · 越线飞书/微信 Webhook · AI Agent

Privora 实时监控——黄金实时监控 / 基金净值监控 / 多资产阈值告警，给一个已订阅资产字段配一条阈值规则（跌破/突破/等于），越线即飞书/微信/通用 Webhook 通知你；港股/美股/A股同样支持。建渠道→建规则→验证→上线，一份文档 11 步走完；Bearer Token 直连 /agent/skills/execute。

Identity and source

Publisher attributionGuangfuWuregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 60% rule confidence
Package forminstruction with code5 recorded files
Canonical sourceClawHub registryclawhub:guangfuwu:privora-alert
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codeissues found
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/31/2026.claude/skills/Privora · 实时监控 for AI Agents
1 structural issue
  • error: name must contain lowercase ASCII letters, numbers and single hyphens only. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexissues found
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/31/2026.agents/skills/Privora · 实时监控 for AI Agents
1 structural issue
  • error: name must contain lowercase ASCII letters, numbers and single hyphens only. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawissues found
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/31/2026skills/Privora · 实时监控 for AI Agents
1 structural issue
  • error: name must contain lowercase ASCII letters, numbers and single hyphens only. SKILL.md

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

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-alert
clawhub inspect @guangfuwu/privora-alert --version 1.0.4

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
5 / 5 inspected as text
Checked
8/31/2026, 12:46:38 PM
Scanner
0.1.3
Policy
1.0.3
2 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
3 dependency and API indicators
  • api: clawhub.ai
  • api: open.feishu.cn
  • api: privora.cn
External clawhub result: suspicious

This 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.

Evidence checked
8/31/2026, 9:32:56 AM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:868d03c765aa0c985992178d3b65ddb427b2578d804bfb64a73e543f7436ec29
Show up to 5 recorded paths
  • CHANGELOG.md
  • scripts/allowed-skills.txt
  • scripts/lg_agent_exec.sh
  • skill-card.md
  • SKILL.md

Source changelog

## v1.0.4 · 2026-08-31 Packaging-narrowing fix (#1037, #1038) — no change to the 11-step flow, the 20-skill set, or any other documented behavior. - **Stopped shipping `lg_agent_list.sh`** (#1037). This package's documented flow never calls it (grep-verified against SKILL.md); shipping it gave a `realtime-alerting` token unfiltered discovery of every skill visible to it — not just this package's 20 — which ClawScan flagged as SDI-1/SDI-2 and rated the published `1.0.3` package `DO_NOT_INSTALL` (score 66 / HIGH). - **`scripts/lg_agent_exec.sh` now ships with a generated `allowed-skills.txt`** derived at packaging time from the `realtime-alerting` preset (18 scopes → 20 skill ids, `lib/skill-catalog.js`'s new `resolvePresetSkillIds`) — the shared wrapper refuses any skill id outside that set. This is a **packaging-honesty control, not a security control**: it is client-side and trivially…