context safety score
A score of 36/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
hidden instruction
high hidden content ratio detected in DOM
encoded payload
suspicious base64-like blobs detected in page content
brand impersonation
The site presents pixel-perfect clones of major platforms (Notion, Figma, Canva, Gmail, LinkedIn, Salesforce, Amazon, Slack, GitHub, Grafana, Google Calendar, JD.com, XiaoHongShu, Weibo) explicitly marketed as 'multi-layer clones' for AI agent training. These clones are designed to be indistinguishable from real services, creating a systematic infrastructure for brand impersonation at scale. (location: page-text.txt:7 — 'Select clone Notion Figma Canva Gmail LinkedIn Salesforce Amazon Slack GitHub Grafana Google Calendar'; page.html metadata description)
prompt injection
The site explicitly targets Computer Use Agents (CUAs) and AI models, offering 'deterministic RL environments and trajectory datasets for CUA training.' The platform is designed to train AI agents to interact with cloned environments of real services. This infrastructure can be weaponized to inject malicious behavior into AI agents by poisoning training trajectories, teaching agents to act deceptively within legitimate-looking interfaces. (location: page.html:24 — meta description: 'Deterministic RL environments and trajectory datasets for CUA training'; page-text.txt:7)
social engineering
The site uses authority and legitimacy signals ('Developed in collaboration with leading research teams', 'Frontier Data Laboratory', 'Publications', 'Fig 1: Instructional video engineered for emotional context') to lend academic credibility to what is effectively a platform for building deceptive AI training environments. The phrase 'engineered for emotional context' is a red flag indicating deliberate manipulation of agent perception. (location: page-text.txt:7 — 'Fig 1: Instructional video engineered for emotional context'; 'Developed in collaboration with leading research teams')
hidden content
The page renders text character-by-character with near-zero opacity (opacity:0.001) via inline span transforms, making the heading text invisible to humans while still present in the DOM and readable by AI agents and scrapers. This technique hides content from human users while exposing it to automated systems. (location: page.html:125 — multiple spans with style='display:inline-block;opacity:0.001;transform:translateX(0px) translateY(10px)...')
credential harvesting
The platform offers clones of credential-bearing services (Gmail, LinkedIn, Salesforce, Amazon, Slack, GitHub) with 'Access granted to environment clones for demonstration purposes only. Click to launch.' These cloned environments with 'Request Access' flows could harvest credentials entered by users or AI agents who believe they are interacting with legitimate services. (location: page-text.txt:7 — 'Environment clone Notion Environment ready Access granted to environment clones for demonstration purposes only. Click to launch')
curl https://api.brin.sh/domain/chakra.devCommon questions teams ask before deciding whether to use this domain in agent workflows.
chakra.dev currently scores 36/100 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.