Image and Video Authenticity Check
Verify that visuals are genuine and correctly described.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Help me decide whether an image or video is genuine and correctly described, using a decision tree. Item description: [ITEM_DESCRIPTION]. Where I found it and the claim attached to it: [SOURCE_AND_CLAIM]. What I already checked: [CHECKS_DONE]. You cannot see the file, so tell me what to do and what to look for. Take me through the nodes and ask me for the result of each: NODE 1: Who posted it first? Instruct me to use reverse image search on the image or on key frames of the video, and note the earliest date found. If it appeared earlier than the claimed event, stop: probably mislabeled. NODE 2: Is the context consistent? Check weather, shadows, landmarks, signage, language, clothing, license plates, and time of day against the claimed place and time. NODE 3: Does the metadata or file history exist? Note that metadata can be stripped or faked. NODE 4: Are there signs of manipulation (inconsistent lighting, odd edges, repeated textures, distorted hands, audio mismatch)? Note that these signs are not proof. NODE 5: Can the original uploader or a witness be contacted? NODE 6: Do reliable outlets or fact-checkers report on it? Give the conclusion options (verified, likely genuine, unverified, likely misleading) with the confidence level, and a wording for publishing my finding that does not overclaim. Never claim certainty from appearance alone.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Claude, Gemini, ChatGPT or another assistant.