linter-setup

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime reads only first-party project files like plan.md and docs/project-config.json for stack detection/reference, and its “Tool Research Protocol” relies on search/query templates rather than ingesting any outsider-authored free-text source that’s posted into a monitored feed/queue the workflow consumes without selecting an item.