The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-defined 'User Journeys' to generate and execute test cases. This creates a standard attack surface for indirect prompt injection where malicious instructions in a user journey could influence the generated test code.
Ingestion points: User journeys and requirements provided in Step 1 of the workflow.
Boundary markers: No explicit boundary markers or 'ignore' instructions are used when interpolating user journeys into test cases.
Capability inventory: The skill instructs the agent to execute shell commands such as npm test and npm run test:coverage (SKILL.md).
Sanitization: No sanitization or validation of the input journeys is described before they are used to generate executable test code.
[COMMAND_EXECUTION]: The skill guides the user and agent to execute standard development commands (npm test, npm run test:coverage) as part of the TDD lifecycle. These are expected behaviors for a software development skill.

tdd-workflow