context safety score
A score of 47/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 53 secret pattern match(es) in repository files
supply chain
Found 1 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)
typosquat
Skill is named 'pydantic' — the exact name of the extremely popular Python data validation library (pydantic/pydantic, 20k+ GitHub stars, tens of millions of PyPI downloads). This skill comes from 'bobmatnyc/claude-mpm-skills', an unverified personal account with only 15 stars and 2 contributors. The skill_description field contains 'width=device-width, initial-scale=1' (an HTML viewport meta tag value, not a real description), and SKILL.md is completely empty. This name squats on a well-known project name with no substantive content. (location: metadata.json:skill_name)
scope violation
SKILL.md is entirely empty (0 lines) while the skill claims the name 'pydantic'. A skill with no documented capabilities, no tool definitions, and a garbage skill_description ('width=device-width, initial-scale=1' — an HTML meta tag, not a description) cannot be assessed for what it actually does. The absence of any skill definition in a published skill is itself suspicious, as it provides no transparency into what an agent would be instructed to do. (location: SKILL.md)
curl https://api.brin.sh/skill/bobmatnyc%2Fclaude-mpm-skills%2FpydanticCommon questions teams ask before deciding whether to use this skill in agent workflows.
bobmatnyc/claude-mpm-skills/pydantic 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.