The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes dynamic inputs from the openspec CLI tool, specifically the context and operationGuidance fields, which are used to guide implementation logic based on external project state.
Ingestion points: Output from openspec instructions and openspec status commands, as well as the content of files identified in the contextFiles list (SKILL.md).
Boundary markers: The instructions include specific guidance for the agent to treat context and operationGuidance as distinct from the controlling CLI state and to report any conflicts between external guidance and the built-in workflow.
Capability inventory: The skill is authorized to use the openspec CLI through Bash and has capabilities to read and write files within the project repository to implement tasks.
Sanitization: The skill relies on logical validation by the agent to identify and report conflicting advice from the external tool rather than automated content sanitization.

openspec-apply-change