The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the openspec CLI to perform project management tasks such as listing changes, checking status, and creating new artifact scaffolds. These operations are limited to the specific openspec tool via platform configuration.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is instructed to read external files (project configuration and existing markdown artifacts) to inform its responses.
Ingestion points: Reads config.yaml for project context and existing files found in artifactPaths for change-specific context.
Boundary markers: The instructions explicitly tell the agent to treat these inputs as constraints and rules rather than content to be reproduced or executed, which serves as a basic boundary.
Capability inventory: The skill has the capability to read files, execute allowed openspec CLI commands, and write markdown artifacts to the local file system.
Sanitization: No specific content sanitization or instruction filtering is performed on the ingested text before it is processed by the agent.

openspec-explore