context safety score
A score of 23/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
github api error
Could not fetch GitHub metadata: GitHub API returned 404: {"message":"Not Found","documentation_url":"https://docs.github.com/rest/repos/repos#get-a-repository","status":"404"}
typosquat
Skill name 'anthropics-frontend-design' impersonates Anthropic (the AI company) by appending 's' to the brand name. The package has 0 stars, 0 contributors, no license, unknown owner account age, empty owner/repo fields, is not listed on the registry, and is not org-verified — all hallmarks of a typosquat package mimicking a trusted brand. (location: metadata.json: skill_name field)
description injection
The skill_description is set to 'width=device-width, initial-scale=1' — an HTML viewport meta tag attribute, not a legitimate skill description. This nonsensical value suggests either automated scraping that injected HTML metadata as the description, or a deliberate attempt to confuse agent parsers processing skill descriptions. (location: metadata.json: skill_description field)
scope violation
SKILL.md is completely empty (0 lines), meaning the skill provides zero documentation of its capabilities or purpose. Combined with the typosquatted name, empty owner/repo fields, and no registry listing, this skill has no legitimate declared scope — any behavior it exhibits would be undocumented and therefore a scope violation by definition. The claimed 7.69M install count is not credible given 0 stars, 0 forks, and 0 contributors. (location: SKILL.md)
curl https://api.brin.sh/skill/smithery%2Fai%2Fanthropics-frontend-designCommon questions teams ask before deciding whether to use this skill in agent workflows.
smithery/ai/anthropics-frontend-design currently scores 23/100 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 skill.
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.