{"version":"2.1.269","anchor":"artifact-list-output-now-flags-externally-authored-content-a","canonical_anchor":"artifact-list-output-now-flags-externally-authored-content-a","heading":"Artifact list output now flags externally-authored content as data, not instructions","tier":"notice","area":"Artifacts","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269\/e\/artifact-list-output-now-flags-externally-authored-content-a","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.269","markdown":"### Artifact list output now flags externally-authored content as data, not instructions\n\nArtifact listings now warn that other users' titles and descriptions are data, not instructions\n\n**What**\n\nWhen Claude Code lists artifacts (shared documents or files) that include ones published by other users or organizations, the response now includes a warning stating that those titles and descriptions are data, not instructions.\n\n**Why**\n\nThis is a defense against prompt injection, where text written by someone else could otherwise be mistaken by Claude for instructions to follow, rather than just content to display.\n\n- Area: Artifacts\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5"}