The Agent Skills Directory

[COMMAND_EXECUTION]: The skill automatically runs a local PowerShell script located at .specify/scripts/powershell/check-prerequisites.ps1 to verify the feature branch environment and repo structure.
[DYNAMIC_EXECUTION]: The skill implements an extension hook system that reads from .specify/extensions.yml. It dynamically constructs command names from hook definitions (e.g., converting dots to hyphens) and triggers them using the EXECUTE_COMMAND directive.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, creating an attack surface where maliciously crafted files could influence agent behavior.
Ingestion points: Data is read from user-provided $ARGUMENTS, project specification files (FEATURE_SPEC), extension configurations (.specify/extensions.yml), and requirement checklists (FEATURE_DIR/checklists/requirements.md).
Boundary markers: The skill uses specific Markdown headers like ## Clarifications to isolate updates, but it does not employ explicit sanitization or instructions to ignore potential commands embedded within the specification text.
Capability inventory: The skill has the ability to execute shell scripts, invoke agent commands via EXECUTE_COMMAND, and write updates to specification and checklist files on the local file system.
Sanitization: No validation or filtering is performed on the content of the hooks or the existing specification text before it is processed or used to trigger subsequent commands.

speckit-clarify