The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx expo install to add the @clerk/expo package and its required peer dependencies, such as expo-secure-store and expo-auth-session, to the project.- [EXTERNAL_DOWNLOADS]: The agent is instructed to fetch configuration data from the Clerk Frontend API (/v1/environment) using the WebFetch tool. This information is used to dynamically identify which authentication strategies are enabled for the project.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes external data from the Clerk API and reads local files within the node_modules directory to guide its code generation and implementation decisions.
Ingestion points: Clerk Frontend API (/v1/environment) and files within the local node_modules/@clerk/expo/ directory.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing these data sources.
Capability inventory: The agent has the ability to modify project files, install packages, and perform network requests.
Sanitization: There is no evidence of explicit sanitization or validation of the fetched configuration or local file content before it is used to influence agent behavior.

clerk-expo