The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external source code, API responses, and test data, creating a potential surface for indirect prompt injection where malicious instructions could be embedded in the data being tested.
Ingestion points: Reads code blocks, external API responses, and user-provided test cases as described in SKILL.md and references/integration-testing.md.
Boundary markers: The skill lacks explicit instructions to use delimiters or ignore embedded instructions when the agent processes or executes the provided code snippets.
Capability inventory: The skill provides instructions for executing shell commands through testing frameworks such as Playwright and Pytest (references/automation-frameworks.md).
Sanitization: No explicit sanitization or validation logic is specified for the input data before processing.
[COMMAND_EXECUTION]: The skill guides the user and agent to execute shell-based testing tools and frameworks, including npx playwright test, npm test, and pytest, which are standard for the intended software quality assurance workflow.
[EXTERNAL_DOWNLOADS]: The documentation and reference guides (e.g., references/automation-frameworks.md) describe workflows that include installing software packages and browser binaries from well-known registries like NPM using commands such as npx playwright install.

test-master