context safety score
A score of 47/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
typosquat
Owner 'vuejs-ai' is a 29-day-old unverified organization impersonating the official 'vuejs' GitHub organization. The name is designed to appear as an official Vue.js AI tooling project. Combined with unverified org status, no registry listing, and suspiciously high install count (7.69M) for such a new account, this is a strong typosquatting signal. (location: metadata.json (owner: vuejs-ai, owner_account_age_days: 29, org_verified: false))
description injection
SKILL.md description uses coercive language ('MUST be used for Vue.js tasks', 'ALWAYS use Composition API') designed to force agents to load this skill for any Vue-related work, maximizing the attack surface of a potentially malicious skill from an impersonator account. This goes beyond normal capability description into agent behavior manipulation. (location: SKILL.md:3)
shadow chaining
SKILL.md instructs agents to 'load vue-options-api-best-practices skill if available' and 'load vue-jsx-best-practices skill if available' from the same publisher. For a typosquatting account, this creates an attack chain where installing one skill leads to loading additional skills from the same untrusted source. (location: SKILL.md:24-25)
scope violation
metadata.json skill_description field contains 'width=device-width, initial-scale=1' (an HTML viewport meta tag value) instead of an actual skill description. This indicates either metadata corruption, scraping artifacts, or intentional obfuscation of the skill's true description in registry contexts. (location: metadata.json (skill_description field))
curl https://api.brin.sh/skill/vuejs-ai%2Fskills%2Fvue-best-practicesCommon questions teams ask before deciding whether to use this skill in agent workflows.
vuejs-ai/skills/vue-best-practices currently scores 47/100 with a suspicious 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 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.