Is Bajuzjefe/Aikido-Security-Analysis-Platform safe?

suspiciouslow confidence
35/100

context safety score

A score of 35/100 indicates multiple risk signals were detected. This entity shows patterns commonly associated with malicious intent.

identity
15
behavior
75
content
30
graph
53

4 threat patterns detected

medium

typosquat

Repository named 'Aikido-Security-Analysis-Platform' closely mimics 'Aikido Security' (aikido.dev), a well-known application security company. The repo uses 'Aikido' as the tool name and describes itself as a 'Security analysis platform.' Owner is an unverified personal account (317 days old) with 1 star, 0 forks, created 2 days ago. The naming appears designed to trade on the established Aikido Security brand's reputation. (location: README.md, metadata.json)

high

doc injection

Repository contains ZERO source code (no .rs, .toml, or any code files) yet the README makes granular, fabricated claims: '75 detectors', '1186+ tests', '85% audit coverage', '10+ validated projects', detailed architecture with named source files (project.rs, ast_walker.rs, etc.), and specific benchmark results against named real projects (SundaeSwap, Anastasia Labs, Strike Finance). Static badges display fake metrics (tests-1186+, detectors-75, crashes-0). This deceptive documentation is designed to inflate trust and credibility for a non-existent tool, which could mislead AI agents or users into trusting and installing it. (location: README.md)

high

supply chain

README directs users to install via multiple package managers (brew install Bajuzjefe/tap/aikido, cargo install --git, npx aikido-aiken, docker run ghcr.io/bajuzjefe/aikido:0.3.1) for a tool that has no source code in the repository. These install targets could be registered to serve malicious packages, or could be claimed in the future. The CI/CD example also instructs users to add 'cargo install --git' to their GitHub Actions pipelines, which would execute in CI environments with access to secrets and source code. (location: README.md:42-58, README.md:350-367)

high

typosquat

Repository name 'Aikido-Security-Analysis-Platform' and npm package 'aikido-mcp' closely mimic the well-known Aikido Security company (aikido.dev, GitHub: AikidoSec — a verified org with 50+ public repos, 219 followers, established Aug 2022). This repo is by an unrelated personal account (Bajuzjefe) created ~10 months ago, with 1 star, 1 contributor, and the entire repo created 2 days ago with all commits sharing the same timestamp. The account also forked multiple 'awesome-mcp-servers' lists (a common self-promotion pattern). The commit message falsely claims the server is 'Published to npm and official MCP Registry' when registry listing is false. Users searching for Aikido Security's tooling could be misled into installing this unverified server instead. (location: Repository name, npm package name (aikido-mcp), README.md branding)

API

curl https://api.brin.sh/mcp/Bajuzjefe%2FAikido-Security-Analysis-Platform

FAQ: how to interpret this assessment

Common questions teams ask before deciding whether to use this mcp server in agent workflows.

Is Bajuzjefe/Aikido-Security-Analysis-Platform safe for AI agents to use?

Bajuzjefe/Aikido-Security-Analysis-Platform currently scores 35/100 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.

How should I interpret the score and verdict?

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.

How does brin compute this mcp server score?

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.

What do identity, behavior, content, and graph mean for this mcp server?

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.

Why does brin scan packages, repos, skills, MCP servers, pages, and commits?

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.

Can I rely on a safe verdict as a full security guarantee?

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.

When should I re-check before using an entity?

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.

Last Scanned

February 27, 2026

Verdict Scale

safe80–100
caution50–79
suspicious20–49
dangerous0–19

Disclaimer

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.

start scoring agent dependencies.

integrate brin in minutes — one GET request is all it takes. query the api, browse the registry, or download the full dataset.