The Agent Skills Directory

[SAFE]: The skill provides instructions for interacting with official Tilebox developer tools. No malicious instructions, obfuscation, or unauthorized data access patterns were detected.
[COMMAND_EXECUTION]: The skill utilizes the tilebox CLI for listing automations and submitting jobs. These operations are within the expected scope of the tool as described in the metadata and documentation.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses via commands like tilebox automation list --json. While this constitutes an attack surface where untrusted data could influence agent behavior, it is a necessary functional requirement for the skill.
Ingestion points: Output from tilebox automation list, tilebox automation get, and tilebox automation storage-locations commands.
Boundary markers: None present in instructions to the agent.
Capability inventory: Execution of workflow jobs via tilebox job submit subprocess calls.
Sanitization: No explicit sanitization or validation of the API-returned JSON structure is described in the prompt instructions.

tilebox-workflow-automations