The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses standard instructional language to guide the agent through TDD workflows. There are no attempts to override safety filters, bypass system constraints, or extract system prompts.
[DATA_EXPOSURE]: No hardcoded credentials or sensitive file paths were found. The code examples in mocking.md correctly demonstrate the use of environment variables (process.env.STRIPE_KEY) for secret management, which is a recommended security practice.
[REMOTE_CODE_EXECUTION]: The skill does not perform any remote package installations or script executions. It is purely instructional and contains no shell commands or network-based download patterns.
[OBFUSCATION]: A thorough scan for zero-width characters, homoglyphs, and encoded content (Base64/Hex) returned no findings. All text and code snippets are clear and readable.
[DYNAMIC_EXECUTION]: There are no instances of eval(), exec(), or runtime code generation. The examples provided are static TypeScript/JavaScript snippets for unit and integration testing.
[INDIRECT_PROMPT_INJECTION]: While the skill instructs the agent to read codebase files and CONTEXT.md, it does not implement any automated processing of untrusted external data that could lead to injection. The capabilities are limited to standard code generation and refactoring guided by the TDD principles.

tdd