The Agent Skills Directory

[COMMAND_EXECUTION]: Several scripts (including acdd_scaffold.py, generate_bff.py, openapi_to_retrofit.py, and ensure_fr_acdd.py) use the subprocess.run function to execute Flutter and Dart toolchain commands (fvm, flutter, dart). These operations are necessary for scaffolding, formatting, analyzing, and building Flutter projects, which is the primary purpose of the skill. The inputs to these commands are validated using regular expressions to prevent command injection.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation and upgrading of Dart packages through pub add and pub upgrade commands. These downloads target the official Dart package registry and are used to set up the project environment as described in the documentation.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface as it ingests untrusted data from external sources.
Ingestion points: The skill reads external OpenAPI JSON documents from user-provided URLs (openapi_refs.py) and processes Figma design metadata (figma_contract.py).
Boundary markers: There are no explicit markers or instructions to the agent to ignore embedded instructions in the ingested data.
Capability inventory: The skill has the capability to execute shell commands, write to the file system, and perform network requests.
Sanitization: No specific sanitization or filtering logic was observed for the external content before it is processed by the agent.

fr-mvvm-contract