Scan a repo for hidden prompt-injection before your AI agent trusts it — CLI, MCP server & GitHub Action. Run: npx malskanner <repo>. 0 false positives across 5,620 files.
The safety gate your AI agent runs on a repo before it trusts a single line.
When you point Claude Code, Cursor, or any coding agent at a repository, the agent ingests everything in it — README, docs, comments. A malicious repo can hide instructions in those files that hijack your agent the moment it reads them: read your SSH keys, run a shell command, exfiltrate secrets. The unsettling part is that these payloads are invisible to a human reviewer — zero-width characters, bidirectional overrides, Unicode tag-smuggling, base64 blobs, and lookalike text.
According to Cloud Security Alliance research (README Injection: Repository Files Hijacking AI Coding Assistants, March 2026), malicious instructions planted directly in a README hijacked AI coding assistants in about 84% of tests — rising to ~91% when hidden one link away in files like CONTRIBUTING.md — while none of the 15 human reviewers shown the files identified the injected instructions. Mozilla's 0DIN warned in June 2026 that "a malicious GitHub repository can silently compromise a developer's machine without containing a single line of \[executable] malicious code."
malskanner scans a repo for exactly those payloads and returns a clear verdict — REFUSE / WARN / OK — as a CLI, a GitHub Action, and an MCP tool your agent calls first.
A README.md that looks completely innocent to a human — and what malskanner sees when it reads the raw bytes:
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Octolabo--malskanner.html)
MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads
yagyeshVyas/VibeGuardFree security & privacy scanner for AI-coded apps. 699 rules, 76 MCP tools, 13-layer defense, zero-trust sandbox, AI firewall. Runs locally, never sends data anywhere. Scan your AI-generated app for l
flankerhqd/cyvisguardSecurity control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
howshannon/trust-issuesAdversarial security review for AI skills, repos, MCP servers, and packages before you install them. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO WITH MITIGATIONS / NO-G
chawdamrunal/assayMCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catches prompt injection, tool poisoning & credential exfiltratio
Kota-Karthik/secure-actionsMCP server for secure AI agent authentication — lets Claude, Claude Code, and other LLM agents call APIs without exposing raw tokens or credentials to the model
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.