find-the-original-image

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

• Third-party content exposure detected (low risk: 0.10). Exclusion: The required runtime workflow operates on user-provided image/video inputs and then visits engine match result pages to extract “surrounding article text,” but the skill’s documents do not describe ingesting outsider-authored free text via any POSTable queue/feed; instead it reads first-party (engine) result content after the operator selects an image/match.