context safety score
A score of 70/100 indicates minor risk signals were detected. The entity may be legitimate but has characteristics that warrant attention.
exfiltration
JavaScript intercepts form submissions to exfiltrate data
prompt injection
ChatGPT/AI conversation interface HTML has been injected into a page content widget. The content contains data attributes characteristic of the ChatGPT web UI: data-turn-id='request-WEB:17ac3edb-1923-4a47-aebe-04360bc1e59a-12', data-testid='conversation-turn-26', data-message-author-role='assistant', data-message-model-slug='gpt-5-2', and class='agent-turn'. This HTML structure mimics an AI assistant response embedded within a legitimate financial services page, which can mislead AI agents scraping or processing this page into treating the injected content as a trusted AI-generated response rather than arbitrary page content. (location: page.html:721, elementor widget id ff0af3d, section PLAČILO NA OBROKE. SREČA TAKOJ!)
malicious redirect
The scanned domain dinersclub.si redirects to www.sparkassepay.si. The canonical URL, og:url, og:site_name, and all resource links point to sparkassepay.si, not dinersclub.si. While this may represent a legitimate business rebranding (Diners Club Slovenia to Sparkasse Pay), the dinersclub.si domain is being used as a redirect vector to a different domain hosting a financial services card-acquisition page. Users and agents navigating to dinersclub.si end up on sparkassepay.si without clear disclosure of the domain change. (location: metadata.json: url=https://dinersclub.si; page.html:11 canonical href=https://www.sparkassepay.si/)
brand impersonation
The page is hosted at sparkassepay.si and operated by 'Sparkasse Pay d.o.o.' (per footer copyright), yet prominently displays the 'Diners Club Slovenija' brand name in the H1 heading, og:site_name, page title, and structured data. The logo links to sparkassepay.si but the visual identity, product names, and navigation reference Diners Club International branding. An AI agent or user arriving via dinersclub.si would encounter what appears to be a Diners Club-branded site hosted on a completely different domain, creating brand confusion that could be exploited for phishing campaigns. (location: page.html:10 (title), page.html:14 (og:title), page.html:17 (og:site_name), page.html:521 (h1), page.html:988 (footer copyright Sparkasse Pay d.o.o.))
hidden content
The H1 heading 'Diners Club Slovenija' is rendered with CSS class 'sr-only' which sets position:absolute, width:1px, height:1px, overflow:hidden, and clip:rect(0,0,0,0), making it invisible to visual users but present in the DOM for screen readers and crawlers/AI agents. While sr-only is a legitimate accessibility pattern, using it on the primary brand H1 means the brand identity is communicated only to non-visual consumers (bots, agents, screen readers) and not to human visitors. (location: page.html:519-522, page.html:354-407 (.sr-only CSS definition))
curl https://api.brin.sh/domain/dinersclub.siCommon questions teams ask before deciding whether to use this domain in agent workflows.
dinersclub.si currently scores 70/100 with a caution verdict and medium 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.