khe-brain-benji

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

• Third-party content exposure detected (low risk: 0.10). The required workflow reads Benji Taylor's own published pieces and skills repo, which are first-party, but the Refresh path (triggered when the user links a piece not in the table) has the agent read an arbitrary user-selected URL whose author is unverified.