The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use curl to query asset information from https://api.xstocks.fi/api/v2/public/assets/{symbol}. This is necessary because the vendor's API blocks standard browser user-agents used by some built-in tools.
[EXTERNAL_DOWNLOADS]: The skill fetches dynamic configuration data (jetton master addresses) from a remote API at api.xstocks.fi. This is an essential function for resolving the correct blockchain contracts for specific stock tokens.
[SAFE]: The skill follows security best practices for blockchain operations:
It requires the agent to call get_jetton_info to verify token details (name, symbol, decimals) before performing swaps.
It mandates using emulate_transaction to preview balance changes before a transaction is sent.
It explicitly requires user confirmation before executing any on-chain transactions.
[PROMPT_INJECTION] (Indirect): The skill possesses a surface for indirect prompt injection as it processes untrusted data from an external API.
Ingestion points: Asset definitions are fetched from https://api.xstocks.fi/api/v2/public/assets/{symbol} (documented in SKILL.md).
Boundary markers: No explicit delimiters are specified for the API response content.
Capability inventory: The skill has access to sensitive tools including send_raw_transaction and emulate_transaction (documented in SKILL.md).
Sanitization: The skill mitigates risks by instructing the agent to verify token metadata using get_jetton_info and to simulate transactions before execution to ensure accuracy.

ton-xstocks