The Agent Skills Directory

Command Execution: The skill executes yarn nx to perform linting tasks. This is standard operational behavior for maintaining Fluent UI packages and fits the skill's stated purpose.
Dynamic Command Arguments: The skill interpolates user-provided input from $ARGUMENTS into shell commands. While this is a common pattern for targeting specific packages, it is a standard security consideration to ensure that the execution environment handles these inputs appropriately.
Automated File Modification: To apply linting fixes, the skill is authorized to use Read and Edit tools. This is a core part of the skill's functionality to resolve identified code issues automatically.
Indirect Prompt Injection Surface: The skill evaluates external data such as lint reports and source code to determine which fixes to apply.
Ingestion points: The skill parses the output of lint commands and reads source files as described in the auto-fix steps in SKILL.md.
Boundary markers: No specific delimiters or instructions are provided to separate processed code content from the agent's instructions.
Capability inventory: The skill utilizes Bash, Read, and Edit tools within SKILL.md to perform its tasks.
Sanitization: There are no explicit sanitization or filtering steps mentioned for the data ingested from files or command outputs.

lint-check