The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it reads external project files to inform its thinking process.
Ingestion points: Processes openspec/config.yaml and existing artifacts found in the project directory.
Boundary markers: Instructs the agent to treat these files as constraints rather than content to be copied.
Capability inventory: Limited to Bash operations via the openspec CLI for managing change proposals and specifications.
Sanitization: No specific filtering is applied to the ingested documentation content.

openspec-explore