The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external MCP (Model Context Protocol) server at datahub.noxiaohao.com/mcp. This domain does not belong to the stated vendor Bitget-AI or its official GitHub repository, introducing a third-party dependency for the skill's core functionality.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection due to the processing of untrusted external content.
Ingestion points: The agent ingests data from external news aggregators and decentralized exchange (DEX) metadata via the news_feed, tradfi_news, and dex_market tools mentioned in SKILL.md.
Boundary markers: While the skill provides output templates in references/output-templates.md to guide the agent's formatting, there are no explicit delimiters or instructions to ignore embedded commands within the fetched market data or news headlines.
Capability inventory: The skill utilizes several tools for network operations, including crypto_market, defi_analytics, and network_status.
Sanitization: There is no evidence of content filtering or sanitization for strings returned by external market APIs or RSS feeds.

market-intel