tailwind-mapping
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute several project-specific commands using pnpm, including utility:dev, dev, storybook, and build, which are typical for frontend development workflows.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external project data (CSS and HTML files) and has the capability to modify files and execute commands. * Ingestion points: The agent is instructed to read configuration and tokens from theme files including root.css, day.css, and night.css. * Boundary markers: No explicit delimiters or instructions are provided to distinguish between valid CSS variables and potentially malicious payloads embedded in the source files. * Capability inventory: The agent has permissions to write to src/css/utility.css, generate documentation in playground/utility/, and execute shell commands via pnpm. * Sanitization: There is no requirement for validation or sanitization of the extracted token names or values before they are used in file generation or command parameters.
Audit Metadata