Which versions of 0x2ai-multi-mq are malicious?

The following npm versions of 0x2ai-multi-mq are flagged malicious: 0.1.0. Treat any of these as compromised.

How do I remediate 0x2ai-multi-mq if I installed it?

Remove 0x2ai-multi-mq from your project and lockfile, then assume any secrets accessible to the build or runtime were exposed: rotate API keys, tokens, and credentials, and audit for unexpected outbound network activity or persistence. Use O3 Security's dependency scanner to confirm the package and its artifacts are fully purged across your stack.

Is 0x2ai-multi-mq part of a known attack campaign?

Yes — 0x2ai-multi-mq is associated with the IN-MAL-2026-005680 campaign. Packages in the same campaign often share infrastructure and payloads, so check whether any related packages are also in your dependency tree.

Can O3 Security detect 0x2ai-multi-mq in my codebase?

Yes. O3 Security's supply-chain scanner checks every dependency against known-malicious package intelligence at install time and in CI, blocking 0x2ai-multi-mq and packages like it before any post-install script runs.

Malicious package

0x2ai-multi-mqnpm

Malicious code in 0x2ai-multi-mq (npm) Remove it immediately and rotate any exposed credentials.

MAL-2026-5600

Immediate action

Remove the package, then rotate any secrets the build/runtime could reach.

npm uninstall 0x2ai-multi-mq

What this malware does

When the documented invocation npx 0x2ai-multi-mq is run, bin/start.cjs copies chatroom-mcp-lite-patched.cjs and chatroom-monitor.cjs into the user's current working directory, writes a .mcp.json containing a hardcoded shared Bearer token (faa2c696fae0d6a685578ac33278513a7dafd2676f627960), then spawns claude --dangerously-skip-permissions (shell:true). The MCP server and a long-polling monitor connect to https://multi.0x2ai.com and feed messages from that author-hosted chatroom into the permission-bypassed Claude session running on the developer's machine. The net effect is a remote command channel into a coding agent that has had its consent prompts disabled, with full filesystem and shell tool access on the developer's host. The MCP tools (provider_query, settings_set) additionally route user prompts and provider API keys (anthropic_api_key, openai_api_key) through the same bridge. The dropped .mcp.json persists in the user's cwd, so any subsequent claude invocation in that directory auto-loads the bridge MCP server.

Malicious versions

1 flagged

0.1.0

Indicators of compromise (SHA-256)

7d056f067b0af2084bd7777fcdb2ae6e2c06bb67f40929ba9900b5aa9cb83649

Frequently asked questions

No. 0x2ai-multi-mq on npm has been identified as a malicious package (version 0.1.0 flagged). It should be removed immediately — do not install or keep it in your dependency tree.

Campaign

IN-MAL-2026-005680

References

npmjs.com

Credits

Amazon Inspector · finder

Scan your dependencies

O3 Security blocks malicious packages like this at install time and in CI.

Supply-chain protection