The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python scripts (build_synastry_data.py and validate_synastry_data.py) to process astrological data. These scripts are bundled with the skill and use standard libraries.
[INDIRECT_PROMPT_INJECTION]: The skill processes birth chart data from external structured_data.md files, which acts as a potential surface for instruction injection if those files contain malicious strings. However, the skill implements isolation rules to protect user privacy.
Ingestion points: Birth chart details from structured_data.md and user-provided relationship metadata.
Boundary markers: None explicitly defined in the processing logic for incoming data.
Capability inventory: The agent has capabilities for file creation, report writing, and local script execution.
Sanitization: Data extraction is performed using specific regex patterns within the provided Python scripts, which serves as a validation layer for the astrological fields.

vedic-synastry