The Agent Skills Directory

[SAFE]: The skill provides structured instructions for a senior test automation engineer to improve code maintainability and organization. It does not include any executable code, shell commands, or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external code (automated tests). While this creates a potential surface for indirect prompt injection via malicious comments or strings in the processed files, the skill does not request or define any sensitive tools (e.g., network access, credential reading) that could be abused. This risk is inherent to the skill's primary purpose of code analysis and refactoring.
[METADATA_POISONING]: The metadata fields (name, description, author, tags) are consistent with the content of the skill and do not contain deceptive instructions or injection attempts.

test-refactor