The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx for executing @redocly/cli and @stoplight/prism-cli. These are well-known utilities from established companies (Redocly and Stoplight) in the API development ecosystem.- [COMMAND_EXECUTION]: The core workflow involves executing linting and mocking commands via the shell (npx @redocly/cli lint openapi.yaml and npx @stoplight/prism-cli mock openapi.yaml). These commands are standard for API design and validation.- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and processing OpenAPI specification files (openapi.yaml), which are then passed to validation tools. This represents a standard attack surface for skills processing external documentation.
Ingestion points: The skill reads and acts upon openapi.yaml as part of its core workflow defined in SKILL.md.
Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the YAML files are present.
Capability inventory: The agent is authorized to execute shell commands via npx as described in SKILL.md.
Sanitization: There is no explicit sanitization step for the content of the API specification before it is processed by the linting tools.

api-designer