The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon external transaction data and user account summaries.
Ingestion points: Data retrieved via get_user_activity, get_user_summary, and get_user_positions tools.
Boundary markers: The instructions do not specify the use of delimiters to separate tool-provided data from system instructions.
Capability inventory: The skill relies on read-only tools to fetch protocol state and transaction history.
Sanitization: There are no explicit instructions to sanitize or validate the content returned by the external API.
[EXTERNAL_DOWNLOADS]: The skill references the official Aave Model Context Protocol (MCP) server at https://mcp.aave.com for its data retrieval operations.

tx-confirmation