The Agent Skills Directory

[SAFE]: The skill implements proactive security measures for handling sensitive mobile app credentials. It explicitly instructs the agent to store service account keys, keystores, and passwords locally within the target project and mandates verification of ".gitignore" settings to prevent accidental credential leakage to version control.
[COMMAND_EXECUTION]: The skill automates release engineering tasks by executing local setup scripts and industry-standard CLI tools (EAS and Fastlane). These operations are essential to the skill's stated purpose of managing mobile store publishing pipelines.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface common to automation tools that parse external configuration data.
Ingestion points: The agent ingests data from "package.json", "app.json", and project directory listings to determine build configurations.
Boundary markers: The instructions do not define specific delimiters or security contexts to differentiate between trusted and untrusted data within these project files.
Capability inventory: The skill possesses shell execution capabilities, including "bash" script execution and interactive build commands through the "eas" CLI.
Sanitization: No explicit sanitization or validation logic is defined for processing metadata from project files before using it in shell command generation.

auto-publish