The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from the local lib/ directory and pubspec.yaml which are external inputs that may contain instructions or malicious patterns targeting the AI auditor.
Ingestion points: The skill reads Dart source files and project configuration files from the local file system using find and grep commands.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions that might be embedded within the source code comments or metadata of the files being audited.
Capability inventory: The skill utilizes shell-based tools for static analysis, including find, grep, wc, and sort. It does not possess network access, file-write capabilities, or arbitrary code execution paths in its current configuration.
Sanitization: The skill does not perform sanitization or filtering of the file contents before they are processed by the agent's logic.

atomic-design-system-auditor