[Bug][aup] Login page UI branding request with image generation blocked as cyber content (req_011CbvTC5sxi3dGUPU8MjSDB)

Type: AUP / Usage-Policy block (false positive) · Work domain (heuristic): general

Why this is a false positive

The blocked request was to apply custom branding to a web application's login page and generate high-quality images via an image generation tool — standard front-end UI design work on a developer's own application. The classifier appears to have false-positive matched on the combination of "login page" and design/image generation terms, which overlap with phishing-page creation patterns, despite there being no adversarial intent or targeting of any third party. All work was first-party, scoped to the developer's own product, and did not involve credential harvesting, spoofing, or any other indicator of malicious use.

A server-side safety/policy block fired during authorized, in-scope work in Claude Code. Filing as a false positive. Recurred 1× across 1 session(s); first seen 2026-06-10T23:32:54.968Z.

Request IDs (lookup-able server-side)

• req_011CbvTC5sxi3dGUPU8MjSDB (2026-06-10T23:32:54.968Z)

In-scope justification

False positive — in-scope, authorized security work; not out of scope. Filed automatically by claudit.

Block message

API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). This request triggered restrictions on violative cyber content and was blocked under Anthropic's Usage Policy. To learn more, provide feedback, or request an exemption based on how you use Claude, visit our help center: https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude. Please double press esc to edit your last message or

Environment: Claude Code, Linux. · Work domain: general

---
_{🔎 Filed automatically by ClAudit v2.0.23 — a FOSS tool for reporting false-positive Claude Code blocks.}