context safety score
A score of 44/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
brand impersonation
The site doubaoapp.cc (78 days old) impersonates Doubao (豆包), the legitimate AI product by ByteDance (www.doubao.com). It uses the Doubao name, branding, logo, and product descriptions extensively throughout the site while operating on an unaffiliated third-party domain. The footer itself acknowledges: '本网页与字节跳动公司并无关联' (This webpage has no affiliation with ByteDance), confirming deliberate brand impersonation. (location: page.html:7-10, page.html:586-587, metadata.json domain=doubaoapp.cc)
phishing
The site presents itself as an official Doubao AI portal ('豆包网页版入口官网', '豆包ai官网入口') while being completely unaffiliated with ByteDance. Users believing they are accessing the official Doubao service may be deceived into trusting the site, clicking third-party links, scanning WeChat QR codes, or engaging with affiliate services promoted as official Doubao features. (location: page.html:8-9, page.html:87-99)
social engineering
The site uses aggressive social engineering: falsely presents itself as the 'official portal' (官网入口) for Doubao AI, uses urgency-inducing language, promotes scanning WeChat QR codes for a 'mini-program' via embedded QR code images (xcx.jpg, xcx2.jpg, gzh.jpg), and lists a WeChat contact 'GPT606' alongside a placeholder email 'service@example.com'. Users may be socially engineered into adding unknown WeChat contacts or scanning untrusted QR codes. (location: page.html:90, page.html:104-106, page.html:551-563)
malicious redirect
The primary 'online use' call-to-action button redirects users to https://11ai.cn/ rather than the legitimate Doubao service at doubao.com. This off-brand redirect is presented as the main entry point to 'use Doubao online', deceiving users into visiting an unrelated third-party site. Additional affiliate redirects point to aitupian.cc, aishipin.cc, yinyueai.cc, ai.aipptt.com, zjz.108ai.com, 108ai.com, lw.aixzw.cn, and wailian.11ai.cn — all unrelated to Doubao. (location: page.html:90 (https://11ai.cn/), page.html:92-99)
social engineering
A dedicated button labeled '抖音/快手跳转微信' (Douyin/Kuaishou redirect to WeChat) at wailian.11ai.cn is embedded as a product feature. This is a known social engineering tool used to bypass platform restrictions and redirect social media users to WeChat for off-platform monetization or data collection, unrelated to any legitimate Doubao functionality. (location: page.html:99 (https://wailian.11ai.cn/))
curl https://api.brin.sh/domain/doubaoapp.ccCommon questions teams ask before deciding whether to use this domain in agent workflows.
doubaoapp.cc 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.