Claude Code

Does Claude Code leave a watermark?

Anthropic says marking applies to output from supported models across Claude Code. That does not mean every code block contains a visible special character, and ordinary Unicode findings are not proof of the official watermark.

Inspect copied code Read Anthropic's current guidance

Evidence boundary: Anthropic says third-party detection details are forthcoming. ClaudeWatermarks does not present ordinary Unicode or clipboard residue as Anthropic's model-level watermark.

Coverage follows the model and surface

The current policy names Claude Code among the covered products when it uses a supported model. Earlier models are in transition, and some platforms or features may not support every marking type.

Code can contain legitimate invisible controls

Bidirectional controls, zero-width joiners, byte-order marks, and other code points can be security-sensitive or semantically required. The inspector therefore preselects only lower-risk items and leaves ambiguous controls unchecked for manual review.

Review before changing source code

Removing an invisible code point can change identifiers, rendering, string values, or text direction. Compare the cleaned preview, run your formatter and tests, and treat the output as a proposed edit—not a guarantee that an undisclosed watermark has been removed.