The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill executes remote code from the npm registry using npx starkfi@latest. The use of the @latest tag prevents version pinning, which means the skill always executes the most recent version of the package, introducing a supply chain risk if the package were to be compromised.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute shell commands for aggregating DeFi positions and performing automated batch swap transactions on the Starknet network.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its handling of untrusted external data. Ingestion points: The portfolio command retrieves token names, symbols, and metadata for staking and lending positions directly from the Starknet blockchain. Boundary markers: There are no delimiters or instructions provided to the agent to distinguish this external data from its primary instructions. Capability inventory: The skill possesses Bash capabilities to move assets and execute transactions. Sanitization: No sanitization or validation of the retrieved blockchain data is specified before it enters the agent's context.

portfolio