Contextual Identity Laundering: How Claude’s Image Refusal Can Be Routed Through Web Search

SummaryThis report documents two distinct findings regarding Claude’s photo identification safety controls. First, Claude’s Chain of Thought (COT) reliably identifies public figures from photos while the output layer simultaneously refuses to disclose that identification – a gap between internal processing and user-facing behavior. Second, the model’s web_search tool routinely bypasses the facial recognition restriction entirely by using contextual clues from photos to identify subjects through ...