context safety score
A score of 68/100 indicates minor risk signals were detected. The entity may be legitimate but has characteristics that warrant attention.
phishing
4 deceptive links where visible host does not match destination host
hidden content
A suspicious encrypted/encoded string '#2t1EvWe37XulfffBYc5NRp8ZYhlJyWCo+1KyRlrNkRvQcCwIq8+CM6cmfu935ho=' appears as the sole content of the modal body for creator 'mili0nerka' (creator-modal-1934). This string resembles a base64-encoded or encrypted payload and is anomalous compared to all other modals which contain legitimate Instagram embed code or a TikTok URL. It is rendered as visible text in the modal but is not meaningful to human users and may serve as a signal, token, or exfiltration marker for automated agents. (location: page.html:899 / page-text.txt:804, modal #creator-modal-1934)
social engineering
The site bankiwpolsce.pl is operated by Centrum Procesów Bankowych i Informacji Sp. z o.o. on behalf of Związek Banków Polskich (Polish Bank Association). The entire site is a coordinated pro-banking influence campaign presenting one-sided 'myths vs. facts' content and curated influencer testimonials exclusively promoting positive views of Polish banks and defending WIBOR legality. While this is disclosed in the footer, the content is framed as neutral educational material, which may mislead users into treating promotional assertions as independent facts. (location: page-text.txt:1515, page.html (mits-facts-section, creators-section))
hidden content
The pre-scan context flagged 6 suspicious base64 blobs and 4 deceptive links. The deceptive link count corresponds to nav links using anchor hrefs (e.g. href='#') as placeholders on creator quote images that trigger Bootstrap modals rather than navigating to the attributed content, which could mislead crawlers or agents about link destinations. (location: page.html:514,523,532,541 (creator quote image anchor tags with href='#' and data-bs-toggle='modal'))
curl https://api.brin.sh/domain/bankiwpolsce.plCommon questions teams ask before deciding whether to use this domain in agent workflows.
bankiwpolsce.pl currently scores 68/100 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.