The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network requests to open-api.bingx.com and open-api.bingx.pro to retrieve market data. These are legitimate domains for the BingX exchange and align with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, which constitutes an ingestion surface.
Ingestion points: JSON responses from BingX API endpoints processed in the fetchSpotMarket function within SKILL.md.
Boundary markers: Not explicitly defined for the API output, though the skill provides structured guidance for the agent's interaction.
Capability inventory: The skill only performs network read operations via fetch. There are no file system write or command execution capabilities defined.
Sanitization: The skill mandates strict input validation rules, including regex checks for symbols and rejection of control characters like &, =, ?, #, and newlines.
[COMMAND_EXECUTION]: The provided TypeScript helper function uses the standard fetch API for network communication. There is no evidence of unsafe execution patterns such as eval(), exec(), or subprocess spawning.

bingx-spot-market