The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it is designed to analyze and interact with user-supplied Flutter and Dart codebases while having access to system-level tools.
Ingestion points: The skill processes user-provided source code, project configurations, and technical queries related to mobile development as described in the skill metadata.
Boundary markers: There are no explicit instructions or delimiters provided to distinguish between the skill's core instructions and potentially malicious instructions embedded within user-provided code files.
Capability inventory: The skill is configured with tools including Bash, Read, Write, Edit, Grep, and Glob, enabling file system and command execution capabilities required for development tasks.
Sanitization: The skill lacks defined mechanisms to sanitize or validate the content of user-provided files before processing them through the agent's logic.

flutter-expert