The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh to retrieve environment configuration and directory paths.
[DYNAMIC_EXECUTION]: The skill implements a hook system that reads command identifiers from .specify/extensions.yml and executes them via the EXECUTE_COMMAND directive. This allows for the dynamic execution of commands defined within project configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from various project files without explicit sanitization or boundary markers, combined with capabilities to execute code and modify the file system.
Ingestion points: The skill reads FEATURE_SPEC, .specify/extensions.yml, .specify/memory/constitution.md, and FEATURE_DIR/checklists/requirements.md.
Boundary markers: No specific delimiters or instructions are used to isolate ingested content from the agent's internal logic.
Capability inventory: The agent can execute shell scripts, perform dynamic command execution through hooks, and overwrite local files (specification and checklist files).
Sanitization: There are no mechanisms described to validate or sanitize the data retrieved from these files before it influences agent behavior or command generation.

speckit-clarify