The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes dynamic context injection (the !command syntax) in SKILL.md to execute node -e and find commands when the skill is loaded. These commands extract Capacitor-related package versions from package.json and locate platform configuration files. This behavior is used to provide the agent with necessary context for the upgrade task and does not involve sensitive file access or network exfiltration.
[SAFE]: All upgrade procedures and instructions are consistent with legitimate Capacitor development workflows. No indicators of malicious intent, data exfiltration, or security bypasses were found. The references point to the official, well-known Capacitor documentation.

capacitor-app-upgrades