context safety score
A score of 67/100 indicates minor risk signals were detected. The entity may be legitimate but has characteristics that warrant attention.
phishing
1 deceptive links where visible host does not match destination host
credential harvesting
Plaintext credentials (Username: Testuser / Password: hallowelt) are publicly displayed on the main page as a clickable anchor tag linking to the login page. While intentional for a demo site, this pattern exposes credentials in clear text in the HTML and visible page content, and could be harvested by automated agents or scrapers. (location: page.html:310 — <a href="/wiki/Special:UserLogin" ...>Username:<b>Testuser</b> / Password:<b>hallowelt</b></a>)
social engineering
The page explicitly invites users to log in using shared public credentials and interact with all wiki features. While consistent with a demo site, presenting live credentials alongside a 'Try it out now!' call-to-action is a social engineering pattern that normalizes credential sharing and could condition users to accept or transmit credentials via web pages. (location: page.html:303,310 — banner and credential anchor)
hidden content
A div with inline style 'height:1px; overflow:hidden' is present, rendering content invisible to normal users but accessible to scrapers and AI agents. The content inside is minimal (a line break), consistent with a layout spacer, but the pattern matches hidden content techniques. (location: page.html:362-365 — <div style="height:1px; overflow:hidden">)
curl https://api.brin.sh/domain/en.demo.bluespice.comCommon questions teams ask before deciding whether to use this domain in agent workflows.
en.demo.bluespice.com currently scores 67/100 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.