clarify

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

• Third-party content exposure detected (high risk: 0.75). The required workflow instructs the agent to “re-read the file” specforge/specs/NNN-slug/clarifications.md and “audit … with the human's raw answers — never summarized,” meaning runtime LLM context can include outsider-authored free text from human answers placed into that file by someone other than the operating user.