context safety score
A score of 44/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
encoded payload
suspicious base64-like blobs detected in page content
social engineering
The site claims to be 'Trusted by 2,000,000+ users' but the domain is only 66 days old. This fabricated social proof is designed to build false trust and lower user defenses before they install a browser extension. (location: page-text.txt, visible hero section: 'Trusted by 2,000,000+ users')
brand impersonation
aichat4search.com presents itself as an independent AI browser extension product ('AI Chat for Search') but all functional feature links route to monica.im, and the footer even labels the monica.im link as 'Ai Chat Chrome Extension'. The site is a thin doorway page masquerading as an original product to capture search traffic and redirect users to a third-party service without disclosure. (location: page.html footer: href='https://monica.im/' with label 'Ai Chat Chrome Extension'; all 24+ feature links point to monica.im)
social engineering
The meta description and page content reference 'Bard' — a Google AI product that was retired and rebranded to Gemini. Using an outdated brand name suggests the page content is stale/cloned and not maintained by a legitimate operator, a pattern common in doorway and affiliate fraud pages. (location: page.html meta description: 'display GPT4, GPT3.5, Claude, and Bard responses')
social engineering
The FAQ explicitly conditions users to expect they must supply active third-party AI provider accounts to use the extension. A browser extension with access to search pages that requires AI provider credentials creates a high-risk surface for credential interception, though no direct harvesting form is present on this landing page. (location: page-text.txt FAQ: 'Do I need an account with an AI provider?' / 'you will need an active account with the respective third-party AI provider')
hidden content
The page title contains a full-width vertical bar character (U+FF5C '｜') instead of a standard ASCII pipe. This Unicode substitution is a common SEO manipulation technique used to game search engine indexing and keyword stuffing detection. (location: page.html <title>: 'AI Chat for Search｜Extension for Enhanced Search')
hidden content
A Portuguese-language link ('reescrever texto' linking to monica.im/pt_BR/tools/rewrite-text) is embedded in an otherwise entirely English-language page with no language toggle. This is a multilingual SEO doorway pattern used to capture non-English search traffic through a page that does not serve those users. (location: page.html footer Productivity section: href='https://monica.im/pt_BR/tools/rewrite-text' label 'reescrever texto')
curl https://api.brin.sh/domain/aichat4search.comCommon questions teams ask before deciding whether to use this domain in agent workflows.
aichat4search.com currently scores 44/100 with a suspicious verdict and low confidence. The goal is to protect agents from high-risk context before they act on it. Treat this as a decision signal: higher scores suggest lower observed risk, while lower scores mean you should add review or block this domain.
Use the score as a policy threshold: 80–100 is safe, 50–79 is caution, 20–49 is suspicious, and 0–19 is dangerous. Teams often auto-allow safe, require human review for caution/suspicious, and block dangerous.
brin evaluates four dimensions: identity (source trust), behavior (runtime patterns), content (malicious instructions), and graph (relationship risk). Analysis runs in tiers: static signals, deterministic pattern checks, then AI semantic analysis when needed.
Identity checks source trust, behavior checks unusual runtime patterns, content checks for malicious instructions, and graph checks risky relationships to other entities. Looking at sub-scores helps you understand why an entity passed or failed.
brin performs risk assessments on external context before it reaches an AI agent. It scores that context for threats like prompt injection, hijacking, credential harvesting, and supply chain attacks, so teams can decide whether to block, review, or proceed safely.
No. A safe verdict means no significant risk signals were detected in this scan. It is not a formal guarantee; assessments are automated and point-in-time, so combine scores with your own controls and periodic re-checks.
Re-check before high-impact actions such as installs, upgrades, connecting MCP servers, executing remote code, or granting secrets. Use the API in CI or runtime gates so decisions are based on the latest scan.
Learn more in threat detection docs, how scoring works, and the API overview.
Assessments are automated and may contain errors. Findings are risk indicators, not confirmed threats. This is a point-in-time assessment; security posture can change.
integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.