The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external market data through various MCP tools, which can then influence the agent's actions.
Ingestion points: Market data is retrieved via get_ticker, get_order_book, get_klines, and get_funding_rate (SKILL.md).
Boundary markers: There are no explicit instructions for the agent to use delimiters or specific safety markers when processing data from the market data tools.
Capability inventory: The skill includes high-impact financial capabilities including create_order, cancel_order, transfer_funds, transfer_spot_futures, and set_leverage (SKILL.md).
Sanitization: The skill does not define any sanitization or validation logic for the external data ingested before it is used in the trading logic.
[COMMAND_EXECUTION]: The skill documentation instructs the user to execute several CLI commands for configuration and testing, which interact with sensitive local configuration paths.
Evidence: The skill mentions running aster-mcp config, aster-mcp list, and aster-mcp test to manage API keys stored in ~/.config/aster-mcp/ (SKILL.md).

aster-trading