The Agent Skills Directory

[SAFE]: The skill consistently enforces security best practices for handling sensitive information. It explicitly instructs users and the AI agent never to place credentials, tokens, or secrets in authentication metadata, registries, logs, or conversion recipes (e.g., in reference/validation.md and reference/canonical-stac-1.1.md).
[SAFE]: Data ingestion processes are governed by strict validation rules. The instructions require verifying source data (XML, JSON, STAC) against documented schemas and specific normalization rules before processing, which mitigates risks associated with processing untrusted external content.
[SAFE]: The skill utilizes official vendor resources, including the tilebox CLI and SDKs (tilebox-python, tilebox-go). References to external repositories (e.g., github.com/tilebox/tilebox-go) are restricted to the author's own infrastructure.
[SAFE]: Code generation mentioned in the Go reference (tilebox dataset generate) is a standard development workflow for protobuf-based systems and includes instructions to commit and inspect the generated code rather than executing it dynamically from untrusted sources.

tilebox-ingesting-datasets