The Agent Skills Directory

[SAFE]: The skill provides mobile development best practices and design principles. It includes a Python script, scripts/mobile_audit.py, which performs static analysis on project files using regular expressions. The script is benign and does not execute the code it reads, nor does it perform any network or file modification operations beyond its stated purpose.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to run the provided scripts/mobile_audit.py. This script execution is local, transparent, and intended for project validation. It does not attempt to gain elevated privileges or interact with sensitive system directories.
[DATA_EXFILTRATION]: No patterns associated with data exfiltration were found. The skill explicitly advises against logging sensitive data and recommends using platform-native secure storage (e.g., Keychain, EncryptedSharedPreferences) for authentication tokens.
[PROMPT_INJECTION]: The skill contains 'anti-memorization' protocols designed to prevent the AI from defaulting to training data patterns. These are benign instructions aimed at ensuring the agent considers the specific context of the user's project rather than using generic templates.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or unsafe handling of secrets were detected. The documentation encourages proper environment variable usage and secure storage practices.

mobile-design