The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for software development workflows. It does not contain any executable code, shell commands, or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to process user-provided bug reports and reproduction steps. This is a standard functional requirement for a developer tool. While this creates an ingestion surface for untrusted data, the skill does not grant the agent any dangerous capabilities or instructions that could be abused through such an injection.

tdd