The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill workflow involves executing standard industry tools via the Node Package Runner (npx).
Evidence: npx @redocly/cli lint openapi.yaml and npx @stoplight/prism-cli mock openapi.yaml are specified in SKILL.md for validating and testing API contracts.
Context: These tools are well-known in the API development community and are used here for their intended technical purposes.
[INDIRECT_PROMPT_INJECTION]: The skill processes external business requirements and domain models to generate API specifications, representing a typical ingestion surface.
Ingestion points: Ingests "business requirements, data models, and client needs" as part of the core workflow in SKILL.md.
Boundary markers: The skill relies on structured output (YAML/JSON) which inherently provides some level of output separation, though explicit instruction delimiters for user input are not defined.
Capability inventory: The skill has the capability to run CLI tools (npx, openapi-generator-cli) and generate code stubs.
Sanitization: No specific sanitization logic is provided, however, the risk is minimized by the technical nature of the output (contract specifications).
[SAFE]: The instructions and reference documents provide high-quality, best-practice-oriented guidance. No evidence of obfuscation, privilege escalation, data exfiltration, or hardcoded credentials was found.

api-designer