01 Crypto Trading Decision Framework

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This is an instruction-only crypto trading decision framework that can influence real-money decisions, but it discloses human-approval limits and has no code, credentials, install steps, or persistence.

This skill appears safe to install as an instruction-only trading framework, but treat its outputs as decision support rather than authorization to trade. Keep human approval mandatory for any live capital movement, and be careful about sharing portfolio or strategy details with multiple LLM providers.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

What this means

If used alongside trading tools or exchange access, the skill could shape financial actions, so the user should remain the final approver.

Why it was flagged

The skill addresses actions that could affect real money, but it explicitly requires human approval and prohibits autonomous execution for those actions.

Skill content
These always require human approval — never autonomous execution:
- New live capital deployment of any size
- Increasing an existing live capital allocation
- Manual close of an open live position
Recommendation

Use it as decision support only; require explicit confirmation before any live trade, capital deployment, position close, or stop-loss change.

What this means

Sensitive financial context could be sent to additional model providers or agents if the user allows multi-model consultation.

Why it was flagged

The skill recommends consulting multiple LLMs for significant capital decisions, which could involve sharing trading strategy or portfolio context beyond the primary agent if such tools are available.

Skill content
4-Model Consensus Rule (for large capital decisions)
1. Primary LLM
2. Second LLM
3. Third LLM
4. Fourth LLM
Recommendation

Before using multi-model review, confirm which providers will receive data and share only the minimum financial details needed.