The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or persistence mechanisms were detected. The skill follows industry best practices for API architecture documentation.
[EXTERNAL_DOWNLOADS]: Mentions using npx to execute @redocly/cli and @stoplight/prism-cli. These are recognized industry-standard tools for API lifecycle management.
[COMMAND_EXECUTION]: Instructs the agent to run CLI commands for linting, mocking, and SDK generation using standard tools such as spectral and openapi-generator-cli for their intended purposes.
[PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting and processing externally supplied OpenAPI specifications.
Ingestion points: OpenAPI YAML/JSON files and business requirement documents provided by the user in the workspace.
Boundary markers: None explicitly defined for isolating untrusted data input.
Capability inventory: Command execution for API validation and mocking tools (redocly, prism, spectral).
Sanitization: None explicitly defined in the instructions; relies on the internal validation logic of the referenced CLI tools.

api-designer