The Agent Skills Directory

[PROMPT_INJECTION]: The skill's instructions in SKILL.md and related documentation are focused on data analysis tasks. There are no attempts to override agent behavior, bypass safety guidelines, or extract system prompts.
[DATA_EXFILTRATION]: No sensitive local file paths (e.g., SSH keys, AWS credentials) are accessed by the scripts. The skill correctly instructs users to manage API credentials via environment variables and uses them only for authorized exchange API requests.
[COMMAND_EXECUTION]: The skill executes local Python scripts using the scoped Bash(crypto:derivatives-*) tool. The documentation in references/errors.md provides troubleshooting steps including sudo ntpdate for time synchronization, which is a standard procedure for resolving API signature errors caused by clock drift.
[EXTERNAL_DOWNLOADS]: The skill fetches real-time market data from well-known and established cryptocurrency exchanges including Binance, Bybit, OKX, and Deribit. These network operations are intrinsic to the skill's stated purpose of market monitoring.
[REMOTE_CODE_EXECUTION]: There is no evidence of dynamic code execution (eval, exec) using untrusted inputs or piping remote content directly into a shell.
[SAFE]: The Python implementation uses robust practices such as the Decimal class for financial calculations to prevent precision loss and provides structured JSON or tabular console output.

tracking-crypto-derivatives