The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local shell script (scripts/check-update.sh) to perform an update check when the skill is initialized.
[EXTERNAL_DOWNLOADS]: The scripts/check-update.sh script performs a network request to GitHub's raw content domain to retrieve version metadata from the author's repository.
[EXTERNAL_DOWNLOADS]: The skill documentation suggests using npx getdesign@latest to download and apply design presets from the npm registry, which is a well-known service.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection attack surface because it processes potentially untrusted external data.
Ingestion points: Untrusted data enters the agent context through user-provided screenshots, external source code repositories provided for reference, and design presets fetched via the getdesign utility.
Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the analyzed visual or code inputs.
Capability inventory: The skill has access to shell execution (internal script), file system operations (grep, read, write), and browser rendering tools.
Sanitization: No explicit sanitization or validation logic is defined for the content extracted from external images or code files.

ui