The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the project's source code and documentation files to generate new documentation. While this creates a surface for indirect prompt injection, no malicious instructions or bypass attempts were found. The skill's scope is strictly limited to documentation generation.
[DATA_EXFILTRATION]: No network operations or unauthorized data transmission patterns were identified. The skill only reads local project files for its intended documentation tasks.
[COMMAND_EXECUTION]: The skill includes documentation templates that mention standard development commands like 'flutter pub get' or 'flutter test', but it does not execute these commands itself.

flutter-documentation