The Agent Skills Directory

[SAFE]: No malicious patterns or security threats were identified. The skill's instructions and the accompanying implementation playbook are aligned with standard software engineering practices and focus on improving code maintainability and quality.\n- [PROMPT_INJECTION]: The skill processes untrusted code provided by the user, representing an indirect prompt injection surface.\n
Ingestion points: User requirements and code are ingested via the $ARGUMENTS variable in SKILL.md.\n
Boundary markers: No explicit delimiters are used in the prompt template to isolate user-supplied code from the system instructions.\n
Capability inventory: The agent is instructed to modify files ("Apply changes") and execute verification steps ("Update tests"), which are standard capabilities for this skill's use case.\n
Sanitization: No input validation or sanitization logic is defined for the processed code.\n- [COMMAND_EXECUTION]: The skill instructions require the agent to "Update tests and verify regressions," which involves executing test runners (such as pytest as shown in the playbook) and other CLI tools in the local development environment. This behavior is expected and consistent with the skill's stated purpose.

code-refactoring-refactor-clean