openspec-apply

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is ingested at runtime via openspec instructions apply --change "<name>" --json and related openspec list --json, whose outputs include contextFiles and task/artifact contents (e.g., proposal/specs/design/tasks) that the workflow then reads and uses for codegraph/implementation.