context safety score
A score of 32/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
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
Brand-new organization account (20 days old), unverified, with repo name 'camp-1' and skill name 'day2-supplement-mcp' designed to appear as educational/bootcamp material. The 7.69M install count is wildly inconsistent with 183 stars, 1 contributor, and a 20-day-old account — strongly suggesting inflated/fabricated metrics to build false trust. (location: metadata.json)
scope violation
The skill_description field contains 'width=device-width, initial-scale=1' — an HTML viewport meta tag value, not a legitimate skill description. This is not a valid description of any tool capability and indicates the metadata was either scraped incorrectly from a web page or deliberately crafted with nonsensical content to bypass description-based analysis. Combined with an empty SKILL.md, the skill has no honest declaration of what it actually does. (location: metadata.json, SKILL.md)
supply chain
The skill has no license, an empty SKILL.md (no documentation), is not listed on any registry, comes from an unverified 20-day-old org with a single contributor, yet claims 7.69M installs. This profile is consistent with a disposable account publishing a potentially malicious or placeholder skill designed to exploit trust signals. Without any actual skill definition visible, the real payload may be delivered through the referenced repository code not included here. (location: .brin-context.md, metadata.json)
curl https://api.brin.sh/skill/ai-native-camp%2Fcamp-1%2Fday2-supplement-mcpCommon questions teams ask before deciding whether to use this skill in agent workflows.
ai-native-camp/camp-1/day2-supplement-mcp currently scores 32/100 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.