osprey-strategy
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The README install steps explicitly fetch and then run remote runtime files and scripts from https://raw.githubusercontent.com/Senpi-ai/senpi-skills/main/osprey/... (and install https://github.com/Senpi-ai/senpi-skills), which would supply the runtime.yaml decision_prompt and executable producer code—so these URLs deliver code and prompts that the agent relies on and will execute.
MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).
- Direct money access detected (high risk: 1.00). The skill is a trading strategy explicitly designed to enter and manage trades on an exchange (XYZ/Hyperliquid). It uses language that indicates order execution and position management: "producer enters", "LONG / SHORT the proxy", "taker-true entry", DSL presets for ladder orders, max_loss, timeouts, and DSL-driven exit behavior. This is a specific tool to buy/sell assets (market orders/position management) rather than a generic capability. Therefore 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