diy-harness

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

• Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the agent’s Turn A explicitly “Explore the project (repo, CMS, Carrd, or mixed)” to write docs/harness-audit.md and generate the readiness score/tasks, meaning it ingests outsider-authored free text from the user’s project contents before selecting specific items.