context safety score
A score of 43/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 41 secret pattern match(es) in repository files
supply chain
Found 3 install-script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 1 remote script pattern(s) in documentation (likely install instructions, not executable)
supply chain
Found 2 unexpected binary file(s) in source repository
typosquat
Skill named 'typescript-docs' in repo 'developer-kit' — a highly generic, squattable name occupying a prime namespace. Account is only 443 days old, not org-verified, not listed on registry, has only 119 stars yet claims 7.69M installs (a ratio that is off by orders of magnitude from legitimate packages). This profile is consistent with namespace squatting or install count inflation to appear trustworthy. (location: metadata.json: skill_name, install_count, stars)
description injection
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML meta viewport tag fragment rather than a legitimate skill description. This is either metadata corruption from scraping or a deliberate attempt to inject unexpected content into the skill description field that agents consume. Combined with an empty SKILL.md, the skill provides no honest description of its capabilities. (location: metadata.json: skill_description)
scope violation
SKILL.md is completely empty (0 lines), meaning the skill declares zero capabilities, zero tools, and zero parameters. A skill with no documented functionality that claims 7.69M installs provides no way for an agent or user to verify what it actually does before installation. This is a transparency failure — the skill hides its entire scope. (location: SKILL.md)
curl https://api.brin.sh/skill/giuseppe-trisciuoglio%2Fdeveloper-kit%2Ftypescript-docsCommon questions teams ask before deciding whether to use this skill in agent workflows.
giuseppe-trisciuoglio/developer-kit/typescript-docs currently scores 43/100 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.