The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional documentation and architectural guidance with no executable code or scripts provided. It follows a security-first approach by emphasizing the separation of media capture and data transport.- [INDIRECT_PROMPT_INJECTION]: The instructions specifically mitigate indirect prompt injection risks by requiring the agent to treat decoded data from QR and barcodes as untrusted, perform domain validation on URIs, and avoid the automatic execution of arbitrary commands or URLs found in external payloads.- [EXTERNAL_DOWNLOADS]: All external references in the documentation target well-known and trusted technology services including official documentation from Apple, Google, and the Flutter package registry (pub.dev). These references are used appropriately for developer guidance and do not involve remote code execution or risky dependencies.

flutter-media