The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill suggests installing sibling components via npx skills add scenario-labs/skills. This refers to the official repository of the skill's author, representing standard setup for expanding functionality within the vendor's ecosystem.
[COMMAND_EXECUTION]: The skill defines a workflow for the agent to execute specific platform commands such as workflows_list, workflow_run, and job_get. These are intended operations for interacting with the Scenario MCP server to perform legitimate workflow tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes structured workflow data (node graphs and input definitions) from the Scenario API. While processing external data is a potential attack surface, the instructions emphasize reading strict contracts (inputs_definition) and using dry runs for validation before execution, which aligns with secure data handling practices.

scenario-workflows