The Agent Skills Directory

Command Execution: The skill utilizes shell commands (via npx openspec) to manage development tasks and query state. This is a core component of the skill's intended functionality for automating technical workflows.
External Package Dependency: The skill relies on openspec, fetched via the npm registry. While this follows standard developer practices for tool distribution, it involves executing code from an external repository.
Indirect Prompt Injection Surface: The skill processes project-specific data (e.g., design docs, task lists) to guide its implementation steps. This represents a potential surface for indirect instructions.
Ingestion points: Reads content from files listed in contextFiles as described in Step 4 of SKILL.md.
Boundary markers: No specific boundary markers or delimiters are defined to isolate data from instructions during processing.
Capability inventory: The skill possesses the ability to execute shell commands and modify local project files.
Sanitization: Content from the external project files is processed directly to perform the requested implementation tasks.

openspec-apply-change