The Agent Skills Directory

[SAFE]: The skill's primary purpose is to provide architectural and testing guidance. All analyzed files contain only markdown documentation and benign code examples.
[DATA_EXFILTRATION]: No network operations or sensitive file access patterns were detected. Code examples correctly demonstrate the use of environment variables for secrets rather than hardcoding them.
[REMOTE_CODE_EXECUTION]: There are no scripts or commands that download or execute remote code.
[PROMPT_INJECTION]: The instructions focus on the TDD workflow and do not contain any patterns intended to bypass AI safety guardrails or override system instructions.
[INDIRECT_PROMPT_INJECTION]: While the skill suggests reading a CONTEXT.md file (which could contain untrusted data), it does not provide any high-risk capabilities (like shell execution or file writing) that could be exploited via indirect injection. The data is used solely for domain vocabulary alignment.

tdd