The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were detected across the skill files. The instructions are focused on software engineering best practices and maintain a clear separation of concerns.\n- [NO_CODE]: The skill consists entirely of markdown instructions, YAML configurations, and JSON scenario files. It does not include any scripts, binaries, or automated installation processes, reducing the risk of unauthorized code execution.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external behavior contracts to modify code, which is a structural attack surface. However, the risk is addressed by the skill's mandatory multi-stage validation process, which requires an honest test failure (RED) and minimal implementation (GREEN) before changes are accepted.

fable-tdd