The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the $ARGUMENTS field in SKILL.md to define API contracts and behaviors.
Ingestion points: SKILL.md processes user-supplied requirements to derive mock service logic.
Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between the API contract data and potential embedded instructions.
Capability inventory: The skill generates Python (FastAPI/Uvicorn) and JavaScript code, implements file-based data storage, and defines network-listening services.
Sanitization: There are no instructions for the agent to sanitize or validate the structural integrity of the provided contract data before generating code templates.
[DYNAMIC_EXECUTION]: The resources/implementation-playbook.md file contains several patterns where executable code is stored as strings to be generated or returned at runtime.
Evidence: The create_dynamic_stub, execute_scenario_sequence, and TestingFrameworkIntegration classes use multi-line strings to store and provide Python and JavaScript source code for mock server implementations.
[EXTERNAL_DOWNLOADS]: The interactive documentation template in resources/implementation-playbook.md references external assets.
Evidence: The HTML template in create_interactive_docs fetches swagger-ui-bundle.js and swagger-ui.css from unpkg.com, which is a well-known and established CDN for NPM packages.

api-testing-observability-api-mock