The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local shell script located at .specify/scripts/bash/check-prerequisites.sh. This allows the execution of arbitrary code contained within the project's repository.
[DYNAMIC_EXECUTION]: The skill implements a hook system that reads commands from .specify/extensions.yml and instructs the agent to execute them via the EXECUTE_COMMAND directive. This pattern allows for the dynamic execution of commands defined in data files without explicit validation.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from multiple project files (spec.md, plan.md, tasks.md, and .specify/extensions.yml) to determine its execution flow and the commands it runs.
Ingestion points: Project configuration and documentation files: .specify/extensions.yml, spec.md, plan.md, and tasks.md.
Boundary markers: None detected. The skill reads and interprets content from these files directly into its logic.
Capability inventory: Shell script execution (check-prerequisites.sh), file creation and appending in the checklists/ directory, and dynamic command execution through extension hooks.
Sanitization: No evidence of sanitization or validation for the commands extracted from extensions.yml or the logic derived from specification files.

speckit-checklist