The Agent Skills Directory

[DATA_EXFILTRATION]: The skill references the RUNWAYML_API_SECRET environment variable for authentication. It includes a specific safety constraint to probe the secret without printing it, which is a defensive measure intended to prevent sensitive credentials from appearing in logs or user-visible output.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data which introduces a theoretical surface for indirect prompt injection.
Ingestion points: The agent fetches documentation from https://docs.dev.runwayml.com/llms.txt and https://docs.dev.runwayml.com/model-routers.md.
Boundary markers: The instructions do not define explicit delimiters to isolate external documentation content from the agent's core instructions.
Capability inventory: The skill provides access to MCP tools that can modify cloud configurations, such as create_model_router and update_model_router.
Sanitization: No specific content sanitization or validation logic is defined for the documentation retrieved from the vendor URLs.
[SAFE]: All identified external resources, including documentation URLs and MCP tools, are hosted on or associated with the author's official runwayml domain and infrastructure.

runway-dev-model-routers