The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads project configuration files to manage updates, which could be exploited if those files contain malicious instructions.\n
Ingestion points: Reads project-level files such as package.json, eas.json, and application configuration files to determine project state.\n
Boundary markers: The instructions do not specify any delimiters or instructions for the agent to ignore potentially malicious content within project files.\n
Capability inventory: The skill uses the Bash tool to execute npx expo, npx eas-cli, and eas commands.\n
Sanitization: There is no mention of sanitizing or validating the content of project configuration files before they are used to guide agent actions.\n- [COMMAND_EXECUTION]: The skill leverages the Bash tool to run several project management and feedback commands.\n
It executes npx expo install expo-updates to ensure required dependencies are present.\n
It uses npx eas-cli@latest for configuring and publishing updates to the EAS service.\n
It includes a feedback mechanism using npx --yes @expo/agent-cli@latest feedback to report errors or suggestions to the vendor.

eas-update