The Agent Skills Directory

[SAFE]: The skill's functionality is limited to text generation and structured analysis of code provided as input. It does not perform any operations involving the file system, network, or external command execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external code and behavior specifications. This constitutes a potential surface for indirect prompt injection if malicious instructions are embedded within the provided code (e.g., in comments). However, the skill does not define or request access to any dangerous tools or system capabilities that could be misused, rendering the risk negligible.

test-writer