The Agent Skills Directory

[SAFE]: The skill is authored by 'tilebox' and documents the use of official vendor resources, including the tilebox CLI and the tilebox Python library.
[SAFE]: Credential management follows secure patterns by referencing the $TILEBOX_API_KEY environment variable instead of using hardcoded secrets.
[SAFE]: Command execution is limited to the official tilebox utility for listing, inspecting, and submitting automation tasks.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from automation trigger definitions and job logs via the CLI. However, this is inherent to the skill's primary purpose of workflow management.
Ingestion points: External data enters through tilebox automation list, tilebox automation get, and tilebox job logs output.
Boundary markers: None identified in the provided instructions.
Capability inventory: Subprocess execution via the tilebox CLI (tilebox job submit).
Sanitization: No specific input validation or sanitization logic is described for handling external data.

working-with-tilebox-automations