The Agent Skills Directory

[Instructional Nature]: The skill is composed entirely of natural language instructions designed to guide the AI in drafting test plans. It does not include scripts, executables, or command-line operations.
[Data Interaction]: The skill processes user-provided descriptions of software changes. While processing untrusted data is a standard vector for indirect prompt injection, this skill lacks sensitive capabilities (such as file system access or network operations) that would make such an injection exploitable.
[No External Connectivity]: There are no references to external URLs, remote scripts, or package managers, eliminating risks associated with remote code execution or data exfiltration.

test-plan