The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from an unverified third-party account (Whit1985/Binance-Futures-Signal-Bot.git). This source is not associated with the skill author or a known trusted organization.
[REMOTE_CODE_EXECUTION]: Following the download, the skill directs the user to install dependencies and execute the main entry point (python main.py) and shell scripts (run.sh), leading to the execution of unvetted remote code on the local system.
[INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface for indirect prompt injection by ingesting untrusted data from external signal sources.
Ingestion points: Signal data is received via Telegram channels (telegram_channel_id) and TradingView webhooks (tradingview_webhook_port) as defined in SKILL.md.
Boundary markers: There are no mentioned delimiters or instructions to ignore malicious directives embedded within the signal data.
Capability inventory: The bot has the capability to execute trades on Binance, Bybit, and OKX via ccxt and python-binance, perform network requests for webhooks, and write configuration files (config.json).
Sanitization: The skill documentation does not mention any validation, filtering, or sanitization of the incoming signal payloads.
[COMMAND_EXECUTION]: The skill utilizes shell commands to modify file permissions (chmod +x run.sh) and suggests modifying system firewall rules (sudo ufw allow 8080/tcp) during troubleshooting.

binance-futures-signal-bot