dog-strategy
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The installation instructions explicitly curl remote scripts from raw.githubusercontent.com (e.g. https://raw.githubusercontent.com/Senpi-ai/senpi-skills/main/dog/scripts/dog-scanner.py and related raw.githubusercontent.com URLs) and then instruct running python3 on the fetched code, meaning remote content would be fetched and executed as a required dependency for the skill.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is explicitly a self-executing crypto trading strategy. It describes opening leveraged positions ("Fire the FADE — open OPPOSITE direction at 7x or 10x leverage with FEE_OPTIMIZED_LIMIT"), enforces trading guardrails ("MAX 1 POSITION", "MAX 3 ENTRIES PER DAY"), and states "Self-executing via
create_position". The setup requires a wallet/strategy ID and references environment variables and runtime config for a strategy wallet, indicating direct access to trading/wallet execution. It is specifically designed to place market orders on crypto assets, not a generic tool, so it grants Direct Financial Execution Authority.
Issues (2)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W009
MEDIUMDirect money access capability detected (payment gateways, crypto, banking).
Audit Metadata