The Agent Skills Directory

[DATA_EXPOSURE]: The skill is designed to access sensitive financial information, including account balances, net liquidation values, and buying power. This is the primary purpose of the skill and is performed via communication with a local Interactive Brokers instance (TWS or IB Gateway).
[COMMAND_EXECUTION]: The skill requires the agent to execute a local Python script (scripts/account.py) using uv or python. This is a standard execution pattern for AI agent skills to perform local tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Interactive Brokers. While this constitutes an attack surface for indirect prompt injection (e.g., if a field in the account summary contained malicious instructions), it is a standard risk for data-ingestion tools and is mitigated by the agent's internal safety filters.
Ingestion points: Data enters the agent's context through the JSON output of scripts/account.py (referenced in SKILL.md).
Boundary markers: None explicitly used in the instruction output.
Capability inventory: The skill executes a Python script that makes local network connections to ports 7496/7497.
Sanitization: The script uses argparse for basic input validation of command-line arguments.

ib-account