The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl commands to interact with the EachLabs Workflows API at workflows.eachlabs.run. This is used for creating workflows, managing versions, and triggering executions.
[EXTERNAL_DOWNLOADS]: Fetches model configuration and schema data from api.eachlabs.ai. These requests are directed to the vendor's official infrastructure.
[PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection where untrusted user data is interpolated into prompt templates for subsequent AI model execution.
Ingestion points: User-supplied variables such as inputs.prompt, inputs.image_url, inputs.narration_text, inputs.script, and inputs.topic are ingested through workflow triggers (identified in SKILL.md and references/WORKFLOW-EXAMPLES.md).
Boundary markers: No explicit delimiters or boundary markers are used to separate user input from the rest of the JSON payload or model instructions.
Capability inventory: The agent performs network operations (curl) to external EachLabs endpoints using these payloads.
Sanitization: There is no evidence of input validation, escaping, or filtering applied to external content before it is interpolated into the workflow steps.

eachlabs-workflows