The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes untrusted content from user-provided URLs and local project files. Maliciously crafted external data could contain hidden instructions that attempt to influence the agent's behavior during the analysis phase. * Ingestion points: SKILL.md instructs the agent to fetch HTML and CSS from external URLs using curl and to read project configuration files. * Boundary markers: No explicit boundary markers or instructions are provided to the agent to ignore or delimit potential commands found within the retrieved web content. * Capability inventory: The agent has permissions to execute shell commands (npx, curl, git) and write files to the local file system. * Sanitization: No input sanitization or filtering is performed on the content retrieved from external sources.
[COMMAND_EXECUTION]: Executes shell commands including curl for fetching external assets, git for locating the project root, and npx for design system validation and export.
[EXTERNAL_DOWNLOADS]: Uses npx to download the @google/design.md package from the NPM registry. This package is hosted under a trusted organization scope.
[REMOTE_CODE_EXECUTION]: Performs remote code execution via the npx utility, which fetches and runs tools from the NPM registry at runtime.

create-design-md