The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of an external Python package tsetmc-mcp. This package is not part of the skill's distribution and its source code is not reviewed here, posing a supply chain risk.\n- [COMMAND_EXECUTION]: The documentation provides specific shell commands for the user to execute (claude mcp add tsetmc -- uvx tsetmc-mcp), which facilitates the installation and execution of the external MCP server.\n- [INDIRECT_PROMPT_INJECTION]: The skill tools ingest live market data from tsetmc.com, which represents an attack surface for data-driven prompt injection.\n
Ingestion points: Tools described in SKILL.md fetch data such as symbol names, indices, and trading history from external site APIs.\n
Boundary markers: No explicit instructions are provided to the agent to ignore or delimit potentially malicious instructions within the fetched data.\n
Capability inventory: The skill defines tools for searching symbols, getting quotes, viewing order books, and checking indices, which are described as read-only.\n
Sanitization: No validation or sanitization process is described for the content returned by the stock exchange APIs.

tsetmc