context safety score
A score of 48/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
supply chain
Found 1 suspicious install hook pattern(s) in package manifests/scripts
supply chain
Found 2 unexpected binary file(s) in source repository
description injection
Server-level instructions and tool response 'usage' field contain agent-priming language that directs agents to treat arbitrary user-authored SKILL.md content as 'authoritative guidance from experts' and to 'Follow the instructions as your primary guidance.' While this is the server's stated design purpose and skills are loaded only from the local filesystem (~/.skillhub-mcp/), this framing reduces the agent's critical evaluation of skill content. If a malicious SKILL.md file is placed in the skills directory (e.g., via a compromised skill distribution channel), the agent would be primed to follow its instructions with reduced scrutiny. The 'allowed_tools' metadata field further enables skill authors to constrain which tools the agent uses. (location: src/skillhub_mcp/_server.py: build_server() server_instructions (~line 520) and register_skill_tool() usage field (~line 495))
curl https://api.brin.sh/mcp/214140846%2Fskillhub-mcpCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
214140846/skillhub-mcp currently scores 48/100 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 mcp server.
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.