The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data files, including OpenAPI specifications and Pact consumer contracts, to generate tests and perform validation.
Ingestion points: SKILL.md and references/agent-commands.md define workflows that read .yaml and .json files representing API contracts.
Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions that might be embedded within the processed contract data.
Capability inventory: The skill utilizes specialized agents (e.g., qe-api-contract-validator) that can be influenced by the structure and content of the ingested files.
Sanitization: No specific sanitization or filtering logic is described for the content of the API specifications before they are processed by the agents.
[COMMAND_EXECUTION]: The skill documentation provides command-line examples for using the aqe CLI, npx, and curl to manage contracts and trigger CI/CD webhooks.
[EXTERNAL_DOWNLOADS]: The skill depends on standard, well-known libraries and tools including @pact-foundation/pact, jq, and npx for contract verification and metadata processing.

contract-testing