The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the 'Bash' tool to execute local Python scripts (scripts/ux_audit.py and scripts/accessibility_checker.py). These scripts are used to perform static analysis on the project's code for accessibility and design compliance. Technical review of the scripts confirms they only perform read operations and regex matching on local files without dangerous system calls or network activity.
[INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it is designed to ingest and process untrusted data from a user-provided project directory.
Ingestion points: scripts/ux_audit.py and scripts/accessibility_checker.py read the content of HTML, JSX, and TSX files within the provided <project_path>.
Boundary markers: Absent. The scripts read file content into strings for pattern matching without using specific delimiters or safety warnings for the agent.
Capability inventory: The skill has access to powerful tools including Read, Write, Edit, Glob, Grep, and Bash.
Sanitization: Absent. The scripts do not sanitize the input files, although they only use the data for predefined regex-based auditing purposes. The risk is considered low given the primary function is static analysis.

frontend-design