The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches example project files and metadata from the official Expo repository on GitHub.
Evidence: Uses gh api to query repository contents and curl to retrieve raw file content from raw.githubusercontent.com/expo/examples.
Evidence: Uses git clone and npx degit to download example directories.
[INDIRECT_PROMPT_INJECTION]: Processes content from external GitHub files, creating a potential surface for indirect prompt injection.
Ingestion points: File contents retrieved from the expo/examples repository via gh and curl (e.g., source code, READMEs).
Boundary markers: Not present; the instructions do not explicitly define markers to separate retrieved code from agent instructions.
Capability inventory: The skill has the ability to execute shell commands (gh, git, npx) and read/write to the local filesystem.
Sanitization: No explicit sanitization or validation of the retrieved content is performed before the agent processes it.
[COMMAND_EXECUTION]: Utilizes various command-line utilities to interact with the repository and manage files.
Evidence: Employs gh, git, npx, and curl to list files, download data, and create new projects.

expo-examples