The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the openspec CLI tool (specifically openspec list --json) to retrieve project context and active change statuses. This command execution is essential for the skill's primary purpose and is restricted to the required tool.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it is designed to read and process content from the local codebase and OpenSpec artifacts which could contain untrusted data.
Ingestion points: The agent reads from codebase files and specific artifact paths such as openspec/changes/<name>/proposal.md, design.md, and tasks.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified when the agent interpolates file content into its context.
Capability inventory: The agent has the capability to execute the openspec CLI and write content to OpenSpec artifact files (specs, designs, tasks).
Sanitization: No sanitization or validation logic is defined for the content ingested from the codebase or artifacts.

openspec-explore