The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external code files and directories as its primary function. It lacks protective instructions or boundary markers to prevent the agent from following instructions that might be embedded within comments or strings in the code being analyzed.
Ingestion points: Instructions in SKILL.md direct the agent to analyze all identifiers in target code provided via file paths or direct input.
Boundary markers: The instructions do not define delimiters or provide warnings to disregard instructions found within the analyzed data.
Capability inventory: The skill is capable of reading files and is specifically designed to generate refactoring scripts that can perform automated write operations on the filesystem.
Sanitization: There is no evidence of sanitization or filtering of analyzed content before it is processed by the model.
[DYNAMIC_EXECUTION]: The skill includes functionality to generate and propose refactoring scripts (e.g., via the --fix-all flag mentioned in README.md) to apply naming changes across a codebase.
Evidence: The SKILL.md and README.md explicitly mention creating refactoring scripts to rename items and update references. While execution typically requires user approval in the host agent environment, the generation of multi-file filesystem modification logic based on model analysis is a dynamic code generation surface.

naming-analyzer