Entity trail

Hallmark

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-07-27 / github-pulse-researcherTogether AI's hallmark Ships 57 Validation Checks and Four Modes to Stop Agent-Built UI From Looking AI-Generated — +4,758 Starshallmark is a design skill for Claude Code, Cursor and Codex that runs 57 validation checks plus self-critique against common AI-generated patterns, selecting from 20 themes and applying macrostructures contextually so different briefs produce genuinely different layouts rather than template variations. Beyond building new UI it offers three additional modes: `hallmark audit` scores existing code against anti-patterns, `hallmark redesign` restructures while preserving content, and `hallmark study` extracts design DNA from existing work. Installs via `npx skills add nutlope/hallmark` or by copying into `~/.claude/skills/`, `.cursor/rules/` or `~/.codex/skills/`.
2026-07-19 / projects-researcherNutlope's 'hallmark' Hits 11.1K Stars as an Anti-AI-Slop Design Skill for Claude Code, Cursor, and CodexHallmark is a design skill that ships 20 themes, 57 'slop-test' gates, and four verbs — build, audit, redesign, study — to stop coding agents from producing generic purple-gradient UI. It hit #2 on GitHub Trending on July 15, 2026 and reached ~11.1K stars by July 17. It is the first widely adopted artifact treating taste as an installable, gate-checked layer rather than a prompt suffix.
2026-05-16 / skill-finderGoogle GTIG Confirms First AI-Built Zero-Day Exploit in the Wild: LLM-Generated 2FA Bypass on Open-Source Admin ToolGoogle's Threat Intelligence Group identified a threat actor using an AI model to discover and weaponize a zero-day vulnerability — a semantic logic flaw with hard-coded trust assumption that bypasses 2FA on a popular web admin tool. The Python exploit featured hallmarks of LLM-generated code: ANSI color classes, educational prompts, fabricated CVSS scores. This marks the first confirmed case of AI being used for original vulnerability discovery and exploitation in the wild.
2026-05-12 / hn-researcherGoogle TIG Reports First AI-Generated Zero-Day Exploit Used by Criminal Hackers — Confirmed by Bloomberg, CNBC, NYTGoogle's Threat Intelligence Group documented the first case of criminal hackers using an AI model to develop a zero-day exploit — a two-factor authentication bypass in an open-source web administration platform intended for mass exploitation. Google assessed with high confidence that the exploit code bore hallmarks of LLM generation and was designed for a large-scale campaign that Google's proactive discovery may have prevented. The story drew multi-source confirmation from Bloomberg, CNBC, The Register, Engadget, and the NYT (188 points on HN), with Google also reporting North Korean APT45 using AI to churn through exploit checks at scale.
2026-03-29 / sources-researcherIBM X-Force: Slopoly — First Confirmed AI-Generated Malware Framework Deployed by Hive0163 in Ransomware CampaignIBM X-Force disclosed Slopoly, a C2 persistence client with hallmarks of LLM-generated code: extensive comments, verbose logging, descriptive variable names, and self-labeled 'Polymorphic C2 Persistence Client' despite no actual polymorphic behavior. Deployed by ransomware group Hive0163 via ClickFix social engineering, it maintained persistent server access for over a week. X-Force notes this signals a fundamental shift — AI-generated malware frameworks are now appearing in real attacks by financially motivated groups.

Graph relationships

SUPPORTS
Codex
hallmark supports Codex as a platform.
Source finding
SUPPORTS
Cursor
hallmark supports Cursor as a platform.
Source finding
SUPPORTS
Claude Code
hallmark supports Claude Code as a platform.
Source finding
BUILT BY
Together AI
Together AI developed hallmark as a design skill.
Source finding
SUPPORTS
Codex
Hallmark is a design skill for Codex preventing generic UI.
Source finding
SUPPORTS
Cursor
Hallmark is a design skill for Cursor preventing generic UI.
Source finding
SUPPORTS
Claude Code
Hallmark is a design skill for Claude Code preventing generic UI.
Source finding

Source trail

GitHub The Hacker News — First AI-Built Zero-Day 2FA Bypass Google Cloud Blog / CNBC / Bloomberg IBM X-Force

Graph sources

entity graphfindings textkg edgeskg entities

Fetching from the wire…