The Agent Skills Directory

[COMMAND_EXECUTION]: The skill workflow includes commands to run npx @redocly/cli lint openapi.yaml and npx @stoplight/prism-cli mock openapi.yaml. These tools are standard for API contract validation and mocking.
[EXTERNAL_DOWNLOADS]: The use of npx involves downloading packages from the public NPM registry at runtime. The specific packages mentioned are maintained by well-known organizations in the API development ecosystem.
[REMOTE_CODE_EXECUTION]: The skill uses npx to fetch and execute external binaries. While this performs remote code execution by design, it targets reputable, versioned utilities for their intended developer-centric purposes.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied or generated openapi.yaml files, which serves as a potential attack surface for indirect prompt injection.
Ingestion points: The openapi.yaml file processed in the core workflow of SKILL.md.
Boundary markers: No explicit markers are used to separate file content from agent instructions during processing.
Capability inventory: The skill has shell execution capabilities via npx (documented in SKILL.md).
Sanitization: No explicit sanitization of the OpenAPI file content is performed before it is passed to external tools.

api-designer