architecture-deepening-review

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

• Third-party content exposure detected (high risk: 0.70). The required workflow instructs the agent to “Read the nearest README, architecture docs, domain glossary, ADRs, and tests when present,” which at runtime will ingest repository-authored prose from the codebase being reviewed (i.e., outsider-authored free text if the operating user did not author that content).