The Agent Skills Directory

[COMMAND_EXECUTION]: The skill processes the project file .specify/extensions.yml to identify and trigger "Extension Hooks." It specifically instructs the agent to emit EXECUTE_COMMAND: {command} for hooks defined in the YAML file, which allows external configuration to drive arbitrary command execution by the agent.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and acts upon instructions found in project configuration files without sanitization.
Ingestion points: Reads content from .specify/extensions.yml, .specify/init-options.json, and .specify/templates/spec-template.md to determine execution logic.
Boundary markers: There are no explicit instructions or delimiters to isolate the content of these files from the agent's core instructions.
Capability inventory: The skill possesses the ability to modify the file system (mkdir, cp, and file writing) and trigger command execution via the EXECUTE_COMMAND marker.
Sanitization: The skill lacks validation or filtering of the configuration file content before using it to generate command outputs.
[COMMAND_EXECUTION]: The skill performs file system operations, including directory creation (mkdir -p) and file copying (cp), using paths derived from project configuration and user input.

speckit-specify