The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill instructions in SKILL.md (lines 18-19) direct the agent to fetch documentation files from https://docs.expo.dev/llms.txt and https://reactnative.dev/llms.txt.
Ingestion Points: Ingests external .txt documentation into the agent's context.
Trust Status: Sources are official domains for Expo and React Native, qualifying for a severity downgrade under the [TRUST-SCOPE-RULE].
[COMMAND_EXECUTION] (INFO): The skill describes the use of standard development CLI tools including npx expo and eas-cli.
Evidence: SKILL.md and references/common-patterns.md contain numerous shell command examples.
Capability: While high-capability (can build and run code), the examples are standard boilerplate for mobile development and do not demonstrate malicious intent or unsafe interpolation of untrusted user input.
[REMOTE_CODE_EXECUTION] (SAFE): No patterns of piping remote scripts to shells (e.g., curl | bash) were detected. The scripts/setup-docs.sh file is a benign shell script used for local environment checks.

react-native-expo