triage-issue-reports

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

• Third-party content exposure detected (high risk: 0.85). The required workflow reads the Slack thread content (root and replies) authored by the reporter/other participants, and that free-form text is then used to generate the verdict that is posted back—so outsider-authored prose from Slack is ingested into the coordinator’s LLM context via the “Read the whole report” / “Freeze source coordinates” thread-reading path.