context safety score
A score of 34/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 8 unexpected binary file(s) in source repository
description injection
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML meta viewport tag value, not a legitimate skill description. This appears to be either scraped HTML metadata injected into the description field or a deliberately malformed description. An agent processing this description would receive nonsensical input, and depending on how description fields are parsed, this could be a vector for HTML/meta injection. (location: metadata.json:skill_description field)
scope violation
SKILL.md is completely empty (0 bytes) and the skill_description is an HTML meta tag fragment, meaning the skill provides zero documentation of what it actually does. A skill named 'web-reader' with 7.69M claimed installs that provides no description, no documentation, and no declared capabilities is fundamentally deceptive — users and agents cannot make informed trust decisions. The complete absence of any capability declaration for a skill is itself a scope violation since all behavior is undocumented. (location: SKILL.md (empty), metadata.json:skill_description)
supply chain
Trust signals are severely inconsistent: 7.69M installs but only 24 stars, 1 contributor, no license, not listed on the registry, not org-verified. The install-to-star ratio (~320,000:1) is astronomically anomalous compared to legitimate packages. This pattern is consistent with install count inflation or a supply chain integrity issue where the reported install count does not reflect genuine adoption. (location: .brin-context.md, metadata.json)
curl https://api.brin.sh/skill/answerzhao%2Fagent-skills%2Fweb-readerCommon questions teams ask before deciding whether to use this skill in agent workflows.
answerzhao/agent-skills/web-reader currently scores 34/100 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.