The Agent Skills Directory

COMMAND_EXECUTION (LOW): The skill instructs the agent to use local shell utilities such as ripgrep (rg), fd, and git to analyze the project structure, dependencies, and code quality. These operations are essential for the skill's purpose and are conducted within the local workspace.
PROMPT_INJECTION (LOW): (Category 8: Indirect Prompt Injection)
Ingestion points: Project source code files are read and analyzed using regex patterns via rg and fd.
Boundary markers: Absent; there are no specific instructions or delimiters used to ensure the agent ignores natural language instructions that might be embedded within the code comments or strings of the project being refactored.
Capability inventory: The agent has capabilities to execute shell commands, manage files (mkdir, mv), and perform git operations.
Sanitization: Absent; codebase content is treated as raw data for analysis.
Automated Scanner Alert (SAFE): The scanner alert for logger.info is a confirmed false positive. The string was identified as a malicious URL likely due to the .info TLD; however, in the context of analysis/quality-assessment.md, it is part of a regex pattern (console.(log|debug|info)) used to identify logging statements for removal or refactoring.

vibecoding-refactor