The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the openspec list --json command to retrieve metadata about active project changes and schemas from the local environment.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it ingests untrusted data from the codebase.
Ingestion points: Reads project artifacts including openspec/changes/*/proposal.md, design.md, tasks.md, and specs/*/spec.md.
Boundary markers: The skill does not define clear boundary markers or instructions to ignore embedded commands when processing these files.
Capability inventory: The skill has capabilities to execute the openspec CLI tool and write/update documentation files within the project structure.
Sanitization: There is no evidence of input sanitization or content validation for the files read from the codebase.

openspec-explore