open-thread

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

• Third-party content exposure detected (high risk: 0.85). In Mode B, the skill reads an outsider-authored tracker ticket (title + body) via the tracker CLI/API and injects that free-form text into the agent’s context to seed the trigger narrative; it also posts a backlink permalink back to the ticket but the injection risk is from the ticket body being ingested.