context safety score
A score of 36/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 9 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)
doc injection
README contains a massive hidden <details> section (collapsed with summary '.') stuffed with 6500+ SEO keywords about ERC-8004, crypto, blockchain, AI agents, and generic search terms ('how to make money with AI', 'how to buy Bitcoin'). This content is entirely unrelated to the stated project purpose (code analysis tool) and is designed to manipulate search engines and AI agent indexing. The hidden nature (single dot as summary label) is deliberately deceptive. (location: README.md:636-863)
doc injection
README promotes an MCP server endpoint at 'modelcontextprotocol.name' — a domain that mimics the official Model Context Protocol domain 'modelcontextprotocol.io'. This domain impersonation could mislead AI agents and users into trusting a third-party endpoint as if it were official MCP infrastructure. The README instructs users to configure their Claude Desktop and other MCP clients to connect to this endpoint. (location: README.md:868-939)
curl https://api.brin.sh/repo/nirholas%2Flyra-intelCommon questions teams ask before deciding whether to use this repository in agent workflows.
nirholas/lyra-intel currently scores 36/100 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 repository.
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.