The Agent Skills Directory

[DATA_EXFILTRATION]: The included verification script (scripts/verify_expo_clerk_setup.py) reads the contents of the project's .env file to confirm configuration. While checking for the publishable key is a functional requirement, .env files are sensitive paths that often contain private credentials.
[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script to validate project setup. This script performs extensive filesystem traversal and reads multiple files within the project directory.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted project files. * Ingestion points: Project source files (.ts, .tsx, .js, .jsx) and the .env file are read by the verification script. * Boundary markers: The script does not use explicit delimiters to isolate project content from the agent's instructions. * Capability inventory: The skill possesses broad execution capabilities through Bash, including package managers and the Expo CLI. * Sanitization: No sanitization or escaping is performed on the contents of the files before they are processed by the script or the agent.
[EXTERNAL_DOWNLOADS]: The skill initiates the download and installation of external Node.js dependencies, such as @clerk/clerk-expo and expo-secure-store, from the npm registry. While these are reputable packages from a well-known service, they represent an external code dependency.

integrating-clerk-expo