The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The instructions in SKILL.md and SKILL_HE.md recommend that users install the TASE MCP server using the command npx github:skills-il/tase-mcp. This process involves downloading and executing code directly from the vendor's public repository to enable live data functionality.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to process external data such as TASE market indices and Maya disclosure filings, which creates a potential surface for indirect prompt injection attacks.
Ingestion points: Data is brought into the agent's context through MCP tools like tase_get_maya_announcements or by the agent reading company reports and market summaries provided by external systems.
Boundary markers: The skill does not define specific delimiters or instructions to help the agent distinguish between its own logic and potentially adversarial instructions embedded in financial reports.
Capability inventory: The skill facilitates financial analysis and tax calculations, and provides the capability to perform network operations through the recommended MCP integration.
Sanitization: There is no evidence of sanitization or filtering logic applied to the content retrieved from external financial disclosure platforms like Maya.

tase-stock-analysis