Crypto Trading Decision Framework
PassAudited by ClawScan on May 13, 2026.
Overview
This is a text-only crypto trading checklist with no code or credential access, but users should treat its trading guidance and any multi-LLM review step carefully.
The provided artifacts appear safe to install as an instruction-only trading framework. Treat it as educational risk-management guidance, not investment advice or permission to trade automatically. Keep human approval for all live-capital actions and avoid sending sensitive portfolio or account details to additional LLMs unless you understand and accept the data-sharing implications.
Findings (2)
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.
The agent may give firm trading recommendations that could influence real-money decisions.
The skill uses strong prescriptive language for financial decisions. This is aligned with its stated risk-management purpose and is mitigated by its human-approval rule, but users should avoid treating it as guaranteed trading authority.
Every trade decision runs through 3 gates — sizing, entry checklist, exit plan. If any gate fails, the trade doesn't happen. No exceptions.
Use this as a checklist, not as automatic trading authorization; verify market data and require explicit human approval for live trades.
If the workflow is followed, portfolio details, strategy logic, or trading intentions could be shared with additional model providers.
The skill recommends involving multiple LLMs for significant capital decisions, but the visible artifact does not define provider identity, consent, or data-minimization boundaries.
4-Model Consensus Rule (for large capital decisions) For any deployment of significant capital: 1. Primary LLM 2. Second LLM 3. Third LLM 4. Fourth LLM
Confirm which services receive the data, redact sensitive account details, and get user consent before using external or additional LLMs.