lore-brief

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow calls lore status --json --since/--until and then uses lore-recall evidence packets for searches/citations; those evidence packets can include outsider-authored free text from Lore artifacts (e.g., issues/wiki/discussion content written by other people) that the LLM ingests into the brief context.