Digital Oracle
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears to be a coherent, mostly read-only market-data analysis tool, with disclosed external API and package-use notes that users should treat cautiously.
This looks reasonable to install if you want an agent to fetch public market data, but be cautious with confidential trading questions, review any optional package installation, and treat the output as analytical context rather than a command to buy, sell, or trade.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Installing the optional package will run third-party code from the Python package ecosystem.
The README documents an optional third-party package install without a version pin. This is purpose-aligned for options-chain analysis, but it is still a supply-chain consideration.
uv pip install yfinance
If using options-chain features, install yfinance from a trusted environment and consider pinning/reviewing the package version.
Questions involving sensitive watchlists, trading ideas, or private research topics could be revealed indirectly through external data requests.
The skill is designed to send requests to multiple external data providers. This is disclosed and necessary for its purpose, but user topics, symbols, or queries may be exposed to those providers.
It plugs into 12 authoritative financial data sources — from prediction markets like Polymarket and Kalshi, to US Treasury yield curves, CFTC institutional positioning, SEC insider trades, central bank rates, and crypto derivatives.
Avoid using confidential trading plans or private business information in queries unless you are comfortable with related market-data lookups leaving your environment.
A user might over-rely on the report when making investment or risk decisions.
The skill uses strong, confidence-building language about market prices. This supports the product concept, but users should not treat generated probabilities as certainty or financial advice.
Markets are efficient. Price contains all public information. Reading price = reading market consensus.
Treat outputs as market-data summaries and probability estimates, not guaranteed predictions or personalized financial advice.