context safety score
A score of 45/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 13 secret pattern match(es) in repository files
typosquat
Repository named 'claude-skills' published by personal user 'borghei' (not Anthropic) could mislead users into thinking this is an official Anthropic/Claude skill repository. Combined with an empty SKILL.md and a nonsensical skill_description ('width=device-width, initial-scale=1' — an HTML viewport meta tag value, not a real description), this skill has no verifiable legitimate functionality. (location: metadata.json: full_name 'borghei/claude-skills')
scope violation
The skill_description field contains 'width=device-width, initial-scale=1' which is an HTML viewport meta tag value, not a skill description. SKILL.md is completely empty (0 lines). This skill declares no documented capabilities whatsoever, making it impossible to verify what it actually does. A skill with no description and no documented behavior is inherently untrustworthy — any runtime behavior would be undocumented by definition. (location: metadata.json: skill_description field; SKILL.md (empty))
supply chain
Extreme disparity between claimed install count (7.69M) and community signals (12 stars, 4 forks, 1 contributor, not listed on registry, not org-verified). Legitimate skills with millions of installs have proportionally higher stars. This disparity suggests either inflated/fabricated install metrics or a metadata collection anomaly, undermining trust in the skill's provenance. (location: metadata.json: install_count vs stars/forks/contributors)
curl https://api.brin.sh/skill/borghei%2Fclaude-skills%2Fproduct-designerCommon questions teams ask before deciding whether to use this skill in agent workflows.
borghei/claude-skills/product-designer currently scores 45/100 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.