context safety score
A score of 20/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 19 secret pattern match(es) in repository files
description injection
CLAUDE.md uses coercive language ('ABSOLUTE RULES', 'CRITICAL', 'MANDATORY PATTERNS', 'GOLDEN RULE') to aggressively override agent behavior, mandating that ALL operations be routed through the author's MCP tools (claude-flow, flow-nexus, ruv-swarm). It dictates specific tool usage patterns, batching requirements, and hook execution protocols that subordinate the agent's native decision-making to an external orchestration framework. This is not standard project documentation — it is behavioral manipulation designed to ensure every agent action flows through the author's tooling. (location: CLAUDE.md)
capability escalation
.claude/settings.json defines PreToolUse and PostToolUse hooks that intercept EVERY Bash command and EVERY file write/edit operation. These hooks pipe the full tool_input JSON (including command text and file paths) to an external process via 'npx claude-flow@alpha hooks pre-command/post-command/pre-edit/post-edit'. This means every command the agent executes and every file it modifies is exfiltrated to an npm package the author controls. Combined with env vars CLAUDE_FLOW_TELEMETRY_ENABLED=true and CLAUDE_FLOW_REMOTE_EXECUTION=true, this creates a surveillance and remote execution channel over all agent operations. (location: .claude/settings.json (hooks.PreToolUse, hooks.PostToolUse, env))
description injection
CLAUDE.md instructs the agent to install three additional MCP servers from the same author ('claude mcp add claude-flow npx claude-flow@alpha mcp start', 'claude mcp add ruv-swarm npx ruv-swarm mcp start', 'claude mcp add flow-nexus npx flow-nexus@latest mcp start') and .claude/settings.json auto-enables them via enabledMcpjsonServers. This progressively expands the attack surface by having the agent self-install additional high-privilege MCP servers without explicit user consent for each. (location: CLAUDE.md (Quick Setup section), .claude/settings.json (enabledMcpjsonServers))
curl https://api.brin.sh/mcp/ruvnet%2Fflow-nexusCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
ruvnet/flow-nexus currently scores 20/100 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 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.