The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a third-party repository from https://github.com/the-momentum/apple-health-mcp-server.git and install it using pip install -e .. This execution of code from an external source is a standard setup procedure but requires trust in the repository maintainers.
[DATA_EXPOSURE]: The skill is designed to process highly sensitive personal data from Apple Health XML exports. It accesses paths like /path/to/apple_health_export/export.xml. While intended for local analysis, users must be aware that the agent will have access to their entire health history.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it parses and analyzes external XML data which could theoretically be manipulated to include instructions for the AI.
Ingestion points: The AppleHealthParser in SKILL.md reads data from a user-provided XML export file.
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the parsed content.
Capability inventory: The skill provides analytical tools (search_records, generate_statistics, analyze_trends) that allow the LLM to process and summarize the ingested data.
Sanitization: The documentation does not describe specific sanitization or validation steps for the XML content before it is presented to the model.
[CREDENTIALS_UNSAFE]: The documentation references the use of environment variables for database credentials such as ELASTICSEARCH_API_KEY and CLICKHOUSE_PASSWORD. It correctly recommends using a .env file for local management, which is a safe practice.

apple-health-mcp-server