digital-oracle
AI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知
No outside reports on file
This skill relies on third-party financial data that can be wrong, outdated, or manipulated; treat its answers as research hints, not investment or policy advice, and never expose real credentials.
Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourceGitHub (komako-workshop/digital-oracle)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/komako-workshop/digital-oracle ↗
Everything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Digital Oracle
A skill for AI agents that fetches and analyzes macro forecasting data from financial prediction markets and regulators (like Polymarket, Kalshi, CFTC, SEC) to answer questions about housing prices, gold, Bitcoin, and geopolitics with probability estimates.
Who it’s for
Developers building AI agents in Claude, Cursor, or similar tools who want macro forecasting insights. Users should understand that prediction market data reflects trader opinions, not guaranteed outcomes.
Alternatives
- OpenMarkets (if available): similar prediction market data aggregation
- Alpha Vantage or Finnhub: real-time financial data APIs for macro indicators
- Manual Polymarket/Kalshi browsing: check markets directly without automation risk
- Traditional macro research tools: Bloomberg Terminal, Trading View, or academic forecast databases
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README on GitHub for installation steps specific to your AI platform (Claude Code, Cursor, or Codex). The repo is at https://github.com/komako-workshop/digital-oracle (opens external site) — check there for exact setup commands and configuration details.
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 906
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Market data as fact: Prediction market probabilities are guesses by traders, not reality; the agent may present them as more certain than they are
- Web scraping risk: If the skill scrapes financial websites, those sites could change format, inject false data, or block requests
- Regulatory data lag: CFTC and SEC data may be outdated by hours or days; the agent won't know this and could give stale advice
- No real-time verification: The skill depends on its data sources; if a source is hacked or manipulated, bad predictions spread to your agent
- Leaking API keys: If you add real API credentials to connect to Polymarket or Kalshi, they could be exposed in logs or code
How to lower the risk
Least-privilege permissions
- Run the skill with read-only access to data sources only
- Never give it ability to execute trades or modify accounts
Network isolation
- Restrict outbound requests to known financial data domains only
- Log all external API calls and review them weekly
Monitoring
- Watch for sudden shifts in probability estimates that don't match news
- Alert if the skill tries to access unexpected URLs or credentials
Red flags to watch for
- Predictions that contradict major news events within hours
- Requests for API keys, passwords, or authentication tokens
- Unusual spike in API call frequency or data volume
Questions
How do I install Digital Oracle?
Digital Oracle does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/komako-workshop/digital-oracle.
Are there security reports about Digital Oracle?
No reports found for this package in our research (last checked 2026-10-30). Digital Oracle currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include market data as fact, web scraping risk, regulatory data lag.
Is Digital Oracle actively maintained?
Digital Oracle has 906 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/komako-workshop/digital-oracle before pinning it in production.
What are alternatives to Digital Oracle?
Notable alternatives to Digital Oracle include OpenMarkets, Alpha Vantage or Finnhub (real-time financial data APIs for macro indicators), Manual Polymarket/Kalshi browsing (check markets directly without automation risk), Traditional macro research tools (Bloomberg Terminal, Trading View, or academic forecast databases). You can also compare Digital Oracle side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Digital Oracle? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/komako-workshop-digital-oracle)HTML embed:
<a href="https://agentarmorhq.com/skills/komako-workshop-digital-oracle"><img src="https://agentarmorhq.com/api/badge/komako-workshop-digital-oracle" alt="AgentArmorHQ Risk Grade for Digital Oracle" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "komako-workshop-digital-oracle"Share with your security lead
Need sign-off to use digital-oracle? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: digital-oracle
- **Listing URL:** https://agentarmorhq.com/skills/komako-workshop-digital-oracle
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 906 GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (komako-workshop/digital-oracle)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/komako-workshop/digital-oracle
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- komako-workshop
- Source code
- github.com/komako-workshop/digital-oracle
- Est. context load
- ~92 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 906 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-23
Community
Discussions for Digital Oracle
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude