The Agent Skills Directory

[PROMPT_INJECTION]: The skill is designed to ingest and process external integration data (migration-schema.json), which contains scripts and metadata from third-party platforms. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the source data to influence the generated TypeScript code.
Ingestion points: Data enters via the migration-schema.json file, specifically through the script_content fields in the scripts and data_transformations sections.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the source content during processing.
Capability inventory: The skill enables the agent to generate complex integration logic and TypeScript code based on the provided schema.
Sanitization: There is no mention of automated sanitization or validation of the Groovy source code or external metadata before it is processed for translation.

migration-framework