The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected in the instructions or metadata.
[DATA_EXFILTRATION]: No sensitive data exposure or exfiltration patterns were found. The skill explicitly advises users to keep signing assets (certificates, keystores, provisioning profiles) and secrets out of version control and use environment variables or secure secret stores instead.
[COMMAND_EXECUTION]: The skill mentions standard development tools such as xcodebuild, Gradle, the Flutter CLI, and React Native/Expo commands. These are used appropriately within the context of mobile application development workflows.
[EXTERNAL_DOWNLOADS]: References to external resources point to well-known and official documentation sites (Apple Developer, Android Developer, Flutter, Expo, React Native) or reputable technology providers. No suspicious remote script executions (e.g., curl|bash) were found.
[OBFUSCATION]: No hidden content, encoded strings, zero-width characters, or homoglyphs were detected across any of the files.
[PRIVILEGE_ESCALATION]: No commands requiring elevated privileges (e.g., sudo) or attempts to modify system-level configurations were identified.
[PERSISTENCE]: No mechanisms for maintaining persistent access, such as modifying shell profiles or cron jobs, were detected.
[DYNAMIC_EXECUTION]: No evidence of dynamic code generation or execution from untrusted sources was found.

mobile-development