The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input via the <feature or change description> parameter in the /gflow:scenario command.
Ingestion points: The feature description provided by the user is interpolated into the analysis instructions.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded instructions within the user input.
Capability inventory: The skill produces structured text (Markdown tables and Gherkin BDD scenarios) intended to be consumed by downstream planning and execution skills. It does not directly execute code or access network resources.
Sanitization: No sanitization or validation logic is defined for the input string.
[EXTERNAL_DOWNLOADS]: The skill includes a reference to an external GitHub repository in its provenance section.
Evidence: Reference to https://github.com/withkynam/vibecode-pro-max-kit is provided for documentation purposes regarding the skill's origin.
Context: This is a static documentation link and does not represent an automated download or execution of remote code.

scenario