task-brief-creator

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

• Third-party content exposure detected (medium risk: 0.30). The skill ingests outsider-authored free text directly from the user’s manual trigger input (Stages 1/2/3 consume it to derive anchors, work type, and brief content), and then may spawn sub-agents for cold-pickup that also receive only the original user input.