context safety score
A score of 32/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.
credential exposure
Found 3 secret pattern match(es) in repository files
supply chain
Found 3 unexpected binary file(s) in source repository
typosquat
Repository is an undeclared copy of aldinokemal/go-whatsapp-web-multidevice (not created via GitHub fork). The entire README, including all clone URLs, Docker images, release links, and Patreon donation links, is copied verbatim from the original. The only addition by samihalawa is a Smithery MCP marketplace badge (@samihalawa/whatsapp-go-mcp), suggesting the repo was created to claim the project on Smithery under a different identity. While the owner account is old (13+ years), the repo has only 5 stars vs the established original. (location: README.md (Smithery badge at line 12; all other content references aldinokemal's project))
supply chain
Pre-compiled Go binaries (whatsapp, whatsapp-mcp) and an archive (whatsapp-go-mcp.tar.gz) are committed directly to the repository and distributed via npm package @samihalawa/whatsapp-go-mcp. The package.json maps bin.whatsapp-go-mcp to the opaque whatsapp-mcp binary. These binaries cannot be verified against source code and could contain arbitrary malicious code including backdoors or credential stealers. The original project (aldinokemal/go-whatsapp-web-multidevice, 3600 stars) uses goreleaser and GitHub Releases for binary distribution and never commits binaries to the repo. (location: whatsapp-mcp, whatsapp, whatsapp-go-mcp.tar.gz, package.json)
supply chain
This repository copies the source code of aldinokemal/go-whatsapp-web-multidevice (3600 stars) without using GitHub's fork mechanism, breaking provenance linkage. The README retains the original's branding, Patreon links, badges, and clone URLs pointing to the original author, while distributing the project under a different name on Smithery.ai (@samihalawa/whatsapp-go-mcp) and npm. The original project already has native MCP support, making this repackaging unnecessary. The owner (samihalawa) has 653 repositories suggesting systematic repackaging. Users searching for WhatsApp MCP on Smithery may unknowingly install this derivative with committed binaries instead of the trusted original. (location: readme.md, smithery.yaml, package.json, SMITHERY_DEPLOYMENT.md)
curl https://api.brin.sh/mcp/samihalawa%2Fwhatsapp-go-mcpCommon questions teams ask before deciding whether to use this mcp server in agent workflows.
samihalawa/whatsapp-go-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 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.