context safety score
A score of 12/100 indicates severe risk signals were detected. This entity exhibits patterns strongly associated with active threats.
tls connection failed
Could not establish TLS connection
exfiltration
markdown/image exfiltration patterns detected
encoded payload
suspicious base64-like blobs detected in page content
malicious redirect
script/meta redirect patterns detected in page source
cloaking
Page conditionally redirects based on referrer or user-agent
exfiltration
JavaScript appears to implement keylogging with exfiltration
exfiltration
JavaScript intercepts form submissions to exfiltrate data
prompt injection
Hidden HTML element contains AI-targeting instructions
curl https://api.brin.sh/domain/www.thesun.ie%2FdetailsCommon questions about this domain and how brin protects your agent.
www.thesun.ie/details currently scores 12/100 with a dangerous verdict and low confidence. brin scored this domain so your agent can decide whether to consume it. Higher scores mean lower risk; lower scores mean your agent should not proceed without review.
Instead of restricting what your agent can do, brin scores every piece of external content before your agent acts on it. Your agent keeps its full capabilities — it just never consumes dangerous content. One API call before every action is all it takes.
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: who published it (identity), how it behaves (behavior), what's actually in it (content), and who else trusts it (graph). Most lookups are resolved by static analysis and registry metadata. When deeper investigation is needed, brin runs its own agent to check for prompt injection, hidden instructions, and social engineering.
The default approach to agent security is guardrails — restrict what the agent can do. It works, but it cripples the agent. brin takes a different approach: let agents operate with full capability and score every piece of external context they consume. You get safety without sacrificing capability.
No. A safe verdict means no significant risk signals were detected in this scan. Assessments are automated and point-in-time. Combine brin scores with your own controls and periodic re-checks.
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.