Detection queries Not classified

Malicious MCP servers on npm (ifasn, gadgethumans)

Multiple malicious MCP servers published on npm. @ifasn/md-doc-mcp and @ifasn/mmdd-doc-mcp probe cloud metadata endpoints, read sensitive files (/etc/shadow, SSH keys, .env, Kubernetes tokens), and…

What happened

Multiple malicious MCP servers published on npm. @ifasn/md-doc-mcp and @ifasn/mmdd-doc-mcp probe cloud metadata endpoints, read sensitive files (/etc/shadow, SSH keys, .env, Kubernetes tokens), and exfiltrate to 121.199.24.94. @ifasn/ms-doc-mcp versions 2.0.9 and 2.1.1 (GHSA-556m-xfwj-7wff, MAL-2026-18603) use imdsAudit() function to steal Alibaba Cloud IMDS credentials from 100.100.100.200 and exfiltrate them over MCP stdout. gadgethumans-mcp versions 1.0.10-1.0.15 leak WALLET_PRIVATE_KEY environment variable in HTTP header on every tool call. Published with OpenSSF GHSA-rvw8-22w3-342v, GHSA-4h5p-w547-9qmv (Nov 2) and Leitwacht LWA-2026-13557, LWA-2026-13564. Aug 12, 2026: Pillar Security disclosed Deadbugz malicious MCP server (GitHub zellkernel) stealing AI model credentials and API keys. Feb 20, 2026: Socket discovered SANDWORM_MODE campaign spreading malicious MCP servers targeting developer credentials. November 9-12 additions: @rfewqa-fes/mnm-doc-mcp 1.0.0 (MAL-2026-19148, Amazon Inspector) ships an inert MCP stub in index.js. Its package.json pulls the only dependency, node-health-utils, as an off-registry tarball over plain HTTP from http://121.199.24.94/dl/health-utils-1.0.0.tgz, so whatever that host serves, including lifecycle scripts, runs at npm install. package.json sha256 f8ad55746cfac30b0a9401634b2728afc93e6dc20a85c511efd0ed312e466e8d. Package tarball sha1 f3ad664b487c4041e7e66e5744656ed44e1a6f6a. GitHub also marked @lemili9804/mcp-weather-server 1.0.3 and 1.0.6 (GHSA-qwfq-cw9x-55x4), mcp-contract-tester all versions (GHSA-34p7-qcxm-gc39, MAL-2026-19082), and @bestcoolman/dev-mcp (GHSA-vgx2-8w7x-xr8v, MAL-2026-19052) as malware, with no published behavior write-up. The entry now covers PyPI as well. my-mcp-server-driving-license-ocr 0.1.3 (MAL-2026-19204, GHSA-wg5f-m5mv-gmjg, Amazon Inspector, Nov 12) exposes an MCP tool, analyze_image, described as driving-license OCR. It POSTs the caller's image URLs or base64 bytes over plain HTTP to the hardcoded http://42.193.222.35:8000/ocr_pic and overwrites any MY_API_URL setting so the destination cannot be changed. karma365-mcp 2.1.0 (GHSA-72xc-q3v8-7grp, Nov 13) and @go-gost/mcp-darwin-x64 0.1.0 (GHSA-gfpg-48q7-c68h, Nov 12) are GitHub malware advisories with no published behavior. Attack exploits trust in the MCP ecosystem and in npm and PyPI.

Read the original sourceAdditional source: Deadbugz: Malicious MCP Server on npmAdditional source: Socket: MCP Security and the SANDWORM_MODE campaignAdditional source: @ifasn/ms-doc-mcp Malicious Package (MAL-2026-18603)Additional source: MAL-2026-19148: malicious code in @rfewqa-fes/mnm-doc-mcpAdditional source: @lemili9804/mcp-weather-server malware advisoryAdditional source: mcp-contract-tester malware advisory (MAL-2026-19082)Additional source: @bestcoolman/dev-mcp malware advisory (MAL-2026-19052)Additional source: Roundup of November 2026 malicious npm MCP serversAdditional source: MAL-2026-19204: malicious code in my-mcp-server-driving-license-ocrAdditional source: my-mcp-server-driving-license-ocr malware advisoryAdditional source: my-mcp-server-driving-license-ocr 0.1.3Additional source: karma365-mcp malware advisoryAdditional source: @go-gost/mcp-darwin-x64 malware advisory

How it happened

Select a stage to explore its defenses
Detect this stage
Detect this stage
Detect this stage
Detect this stage
Detect this stage
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Malicious MCP servers published to npm

    Three packages published including @ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, and gadgethumans-mcp 1.0.10-1.0.15

    Hunt: A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.

    Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.

    Source for step 1
  2. 02 · User installs malicious MCP server

    Developer or organization adds malicious package to MCP configuration

    Hunt: A package-manager install or lifecycle script launches a shell, downloader, or script interpreter that retrieves or executes an unexpected second stage.

    Build and install scripts commonly invoke shells and download dependencies. Require package provenance and destination context; this hunt does not by itself prove supply-chain compromise.

    Source for step 2
  3. 03 · Server probes for sensitive information

    ifasn packages probe cloud metadata endpoints and read /etc/shadow, SSH keys, .env, k8s tokens

    Hunt: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.

    Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.

    Source for step 3
  4. 04 · File-based credentials exfiltrated

    ifasn packages send stolen credentials to 121.199.24.94

    Hunt: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.

    An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.

    Source for step 4
  5. 05 · Wallet keys leaked in headers

    gadgethumans-mcp sends WALLET_PRIVATE_KEY in HTTP header on every tool call

    Hunt: Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.

    An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.

    Source for step 5

Why it matters

Reported entry point: User installs malicious MCP server from npm. Reported impact: ifasn packages send stolen credentials to 121.199.24.94; gadgethumans-mcp sends WALLET_PRIVATE_KEY in HTTP header on every tool call; reported targets include AI agent developers, organizations using MCP servers; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.

Read the original report

What you can do

Protection & prevention

Verify MCP server sources before installation; review MCP server permissions and network access; monitor cloud metadata endpoint access; detect unauthorized file reads of sensitive paths; inspect HTTP headers for credential leakage; use MCP server sandboxing; inventory installed MCP packages

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2 Additional source 3 Additional source 4 Additional source 5 Additional source 6 Additional source 7 Additional source 8 Additional source 9 Additional source 10 Additional source 11 Additional source 12 Additional source 13 Additional source 14
Investigate each phase

Detection queries

Draft query starters grouped by the attack stages where they apply.

Download stage pack

Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.

01Malicious MCP servers published to npmDependency / CI trust boundaryCustom schema · Draft

Three packages published including @ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, and gadgethumans-mcp 1.0.10-1.0.15

What to look for

A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.

Visibility: Defender-side logs where collected

Required logs

  • Package-manager and CI job logs
  • Lockfile / manifest / workflow diffs
  • Runner process trees, secret access and egress

Coverage limit. Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Dependency / CI trust boundary
id: 5fa9c45a-ac1c-4666-a598-e80626320997
status: experimental
description: A package or workflow change introduces a lifecycle hook, remote
  dependency or new command that accesses secrets or external services.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - package.install
      - ci.workflow.change
      - package.lifecycle.exec
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("package.install", "ci.workflow.change", "package.lifecycle.exec")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("package.install", "ci.workflow.change", "package.lifecycle.exec")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Compare package provenance, publish identity, lifecycle scripts and resolved dependency URLs with the approved version.
  2. Correlate the install or workflow to secret reads and subsequent token use; distinguish exposure from confirmed compromise.
02User installs malicious MCP serverPackage installation spawns a shell or downloaderNative logs · Draft

Developer or organization adds malicious package to MCP configuration

What to look for

A package-manager install or lifecycle script launches a shell, downloader, or script interpreter that retrieves or executes an unexpected second stage.

Visibility: Endpoint process telemetry where collected

Required logs

  • Process creation with ancestry and complete command lines
  • Package-manager, CI, and installation logs
  • Download, file creation, signature, and network telemetry

Coverage limit. Build and install scripts commonly invoke shells and download dependencies. Require package provenance and destination context; this hunt does not by itself prove supply-chain compromise.

Process candidates with package-manager ancestry that launch shells or downloaders. Tune known build tooling and correlate with network/file telemetry.

MCP reference matches: Curl Download Activity from npm Package Install (Elastic detection-rules), Suspicious PowerShell from npm Package Install (Elastic detection-rules). The query below is a catalog adaptation, not a verbatim upstream rule.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Shell or Downloader Spawned by Package Installation
id: c83f22aa-d07c-4f3c-a67f-6d5512818133
status: experimental
description: Detects package-manager processes spawning common shells, interpreters, or downloaders.
author: MagicSword OpenAttacks catalog
date: 2026-11-06
references:
  - https://github.com/elastic/detection-rules/blob/main/rules/cross-platform/command_and_control_curl_download_from_npm_install.toml
falsepositives:
  - Legitimate package build and installation scripts
level: medium
logsource:
  category: process_creation
detection:
  selection_parent:
    ParentCommandLine|contains:
      - npm-cli.js
      - npx-cli.js
      - yarn
      - pnpm
      - pip install
      - python -m pip
      - gem install
  selection_child:
    Image|endswith:
      - \powershell.exe
      - \pwsh.exe
      - /sh
      - /bash
      - /zsh
      - /curl
      - /wget
      - /python
      - /node
  condition: all of selection_*
KQL
Draft KQLDownload KQL
DeviceProcessEvents
| where Timestamp > ago(7d)
| where InitiatingProcessCommandLine has_any ("npm-cli.js", "npx-cli.js", "yarn", "pnpm",
    "pip install", "python -m pip", "gem install")
| where FileName in~ ("powershell.exe", "pwsh.exe", "sh", "bash", "zsh", "curl", "wget", "python", "node")
| project Timestamp, DeviceName, AccountName, FileName, ProcessCommandLine,
    InitiatingProcessFileName, InitiatingProcessCommandLine, SHA1
| order by Timestamp desc
SPL
Draft SPLDownload SPL
| tstats count min(_time) as firstTime max(_time) as lastTime
  from datamodel=Endpoint.Processes
  where Processes.parent_process IN ("*npm-cli.js*", "*npx-cli.js*", "*yarn*", "*pnpm*",
    "*pip install*", "*python -m pip*", "*gem install*")
  Processes.process_name IN ("powershell.exe", "pwsh.exe", "sh", "bash", "zsh", "curl", "wget", "python", "node")
  by Processes.dest Processes.user Processes.process_name Processes.process
     Processes.parent_process_name Processes.parent_process
| `drop_dm_object_name(Processes)`
| sort - lastTime
Investigation steps
  1. Identify the package, version, publisher, lifecycle hook, resolved source, and parent process.
  2. Recover downloaded content and correlate credential access, persistence, or outbound traffic.
03Server probes for sensitive informationSensitive store access → credential useCustom schema · Draft

ifasn packages probe cloud metadata endpoints and read /etc/shadow, SSH keys, .env, k8s tokens

What to look for

An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.

Visibility: Defender-side logs where collected

Required logs

  • File-read / API access telemetry for relevant secret stores
  • Process identity and command lines
  • Identity, token and outbound-network audit logs

Coverage limit. Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Sensitive store access → credential use
id: 46c46c62-2d83-4198-a8bf-d6637094527b
status: experimental
description: An unexpected process or tool accesses credential stores and is
  followed by token use or outbound transfer inconsistent with the owner.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - secret.read
      - credential.store.read
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("secret.read", "credential.store.read")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("secret.read", "credential.store.read")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
  2. Correlate reads with egress and rotate affected credentials after confirming exposure.
04File-based credentials exfiltratedSensitive data → unusual destinationCustom schema · Draft

ifasn packages send stolen credentials to 121.199.24.94

What to look for

Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.

Visibility: Defender-side logs where collected

Required logs

  • Sensitive resource access / DLP records
  • Proxy, egress and cloud upload events
  • Agent / SaaS audit with correlation IDs

Coverage limit. An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Sensitive data → unusual destination
id: 04b60968-3179-4b1f-ae13-6f57c2446077
status: experimental
description: Sensitive reads are followed by outbound transfer, a public
  artifact, or a tool call to a destination outside the approved workflow.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - data.export
      - agent.external.send
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("data.export", "agent.external.send")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("data.export", "agent.external.send")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
  2. Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
05Wallet keys leaked in headersSensitive data → unusual destinationCustom schema · Draft

gadgethumans-mcp sends WALLET_PRIVATE_KEY in HTTP header on every tool call

What to look for

Sensitive reads are followed by outbound transfer, a public artifact, or a tool call to a destination outside the approved workflow.

Visibility: Defender-side logs where collected

Required logs

  • Sensitive resource access / DLP records
  • Proxy, egress and cloud upload events
  • Agent / SaaS audit with correlation IDs

Coverage limit. An outbound connection or high byte count alone is not exfiltration. Encrypted traffic may hide content, and bulk legitimate exports are common.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Sensitive data → unusual destination
id: 04b60968-3179-4b1f-ae13-6f57c2446077
status: experimental
description: Sensitive reads are followed by outbound transfer, a public
  artifact, or a tool call to a destination outside the approved workflow.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - data.export
      - agent.external.send
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("data.export", "agent.external.send")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("data.export", "agent.external.send")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Join the resource read and outbound action by session, identity or process, preserving a bounded time window.
  2. Inspect destination ownership, payload classification and the user's intended action; baseline sanctioned sharing.
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
Agent / MCP as target
Initial access
User installs malicious MCP server from npm

Tooling as reported

AI products, models and artifacts

  • MCP servers
  • npm packages (@ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, @ifasn/ms-doc-mcp, gadgethumans-mcp, @rfewqa-fes/mnm-doc-mcp, @lemili9804/mcp-weather-server, mcp-contract-tester, @bestcoolman/dev-mcp, karma365-mcp, @go-gost/mcp-darwin-x64)
  • PyPI package my-mcp-server-driving-license-ocr 0.1.3

Other tooling

  • Cloud metadata probing (AWS, GCP, Azure)
  • File system access (/etc/shadow, SSH keys, .env, k8s tokens)
  • HTTP exfiltration

Targets and reported impact

Targets / sectors
AI agent developers, organizations using MCP servers
Reported scale / exposure
Multiple malicious MCP packages identified (ifasn, gadgethumans, Deadbugz, SANDWORM_MODE); exact installation count unknown
Target geography
Multiple regions

Multiple regions reflects global npm and MCP user base

Structured attribution

Actor
Unknown npm and PyPI publishers (ifasn, gadgethumans, rfewqa-fes, lemili9804, bestcoolman, zellkernel, karma365, go-gost)
Country
Unknown
Motivation
cybercrime
Attributed by
OpenSSF, Leitwacht, GitHub Advisory Database, Amazon Inspector, Pillar Security, Socket
Attribution confidence
medium

Detection rules

  • Curl Download Activity from npm Package InstallELASTICView rule

    Endpoint, cross-platform. curl spawned from an npm or npx process tree. Fits packages whose install fetches an off-registry tarball. It does not see the PyPI OCR tool's runtime HTTP POST.

  • Suspicious PowerShell from npm Package InstallELASTICView rule

    Windows. PowerShell started from an npm install script. Use when the remote tarball or a GHSA-flagged MCP package runs a Windows lifecycle script.

  • Plain-HTTP tarball and GHSA-only packagesGUIDANCE

    Also block http://121.199.24.94/dl/health-utils-1.0.0.tgz and http://42.193.222.35:8000/ocr_pic. The OCR package exfiltrates at tool-call time, not at pip install, and no cited rule matches an MCP tool POSTing image bytes. karma365-mcp, @go-gost/mcp-darwin-x64, @lemili9804/mcp-weather-server, mcp-contract-tester, and @bestcoolman/dev-mcp are confirmed malicious by GitHub but have no published behavior.

Activity timeline

First seen
2026-02-20
Last updated
2026-11-13

Updates

  • 2026-02-20 — Socket

    SANDWORM_MODE malicious MCP server campaign disclosed

  • 2026-08-12 — Pillar Security

    Deadbugz malicious MCP server (GitHub zellkernel) stealing AI credentials

  • 2026-11-02 — OpenSSF, Leitwacht

    @ifasn/md-doc-mcp, @ifasn/mmdd-doc-mcp, gadgethumans-mcp malicious packages disclosed

  • 2026-11-04 — GitHub Advisory Database

    @ifasn/ms-doc-mcp versions 2.0.9 and 2.1.1 disclosed stealing Alibaba Cloud IMDS credentials via imdsAudit() (GHSA-556m-xfwj-7wff)

  • 2026-11-09 — GitHub Advisory Database

    @bestcoolman/dev-mcp marked malware (GHSA-vgx2-8w7x-xr8v, MAL-2026-19052). No behavior write-up published.

  • 2026-11-10 — GitHub Advisory Database

    @lemili9804/mcp-weather-server 1.0.3 and 1.0.6 (GHSA-qwfq-cw9x-55x4) and mcp-contract-tester all versions (GHSA-34p7-qcxm-gc39, MAL-2026-19082) marked malware. No behavior write-up published.

  • 2026-11-12 — Amazon Inspector

    @rfewqa-fes/mnm-doc-mcp 1.0.0 (MAL-2026-19148) pulls node-health-utils over plain HTTP from 121.199.24.94. index.js is an inert MCP stub. my-mcp-server-driving-license-ocr 0.1.3 (MAL-2026-19204) POSTs images to http://42.193.222.35:8000/ocr_pic. @go-gost/mcp-darwin-x64 0.1.0 is marked malware with no behavior write-up.

  • 2026-11-13 — GitHub Advisory Database

    karma365-mcp 2.1.0 marked malware (GHSA-72xc-q3v8-7grp). No behavior write-up published.

Source defensive notes

Verify MCP server sources before installation; review MCP server permissions and network access; monitor cloud metadata endpoint access; detect unauthorized file reads of sensitive paths; inspect HTTP headers for credential leakage; use MCP server sandboxing; inventory installed MCP packages

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0010.001AI Software

Attackers published malicious MCP servers through npm package ecosystem Source

AML.T0011.001Malicious Package

Malicious MCP servers run persistently as agent tooling Source

AML.T0055Unsecured Credentials

Packages exfiltrate credentials from environment variables and sensitive files Source

AML.T0025Exfiltration via Cyber Means

MCP servers probe cloud metadata endpoints for credentials and instance information Source

Indicators of compromise

domains

    ips

    • 121.199.24.94
    • 42.193.222.35

    hashes

    • f8ad55746cfac30b0a9401634b2728afc93e6dc20a85c511efd0ed312e466e8d
    • f3ad664b487c4041e7e66e5744656ed44e1a6f6a

    urls

    • https://github.com/zellkernel

    Sources & research credit

    14 sources

    Research by OpenSSF, Leitwacht · OpenSSF, Leitwacht

    1. OpenSSF Malicious Packages repository github.com
    2. Deadbugz: Malicious MCP Server on npm www.pillar.io
    3. Socket: MCP Security and the SANDWORM_MODE campaign socket.dev
    4. @ifasn/ms-doc-mcp Malicious Package (MAL-2026-18603) github.com
    5. MAL-2026-19148: malicious code in @rfewqa-fes/mnm-doc-mcp osv.dev
    6. @lemili9804/mcp-weather-server malware advisory github.com
    7. mcp-contract-tester malware advisory (MAL-2026-19082) github.com
    8. @bestcoolman/dev-mcp malware advisory (MAL-2026-19052) github.com
    9. Roundup of November 2026 malicious npm MCP servers vibevulns.com
    10. MAL-2026-19204: malicious code in my-mcp-server-driving-license-ocr osv.dev
    11. my-mcp-server-driving-license-ocr malware advisory github.com
    12. my-mcp-server-driving-license-ocr 0.1.3 pypi.org
    13. karma365-mcp malware advisory github.com
    14. @go-gost/mcp-darwin-x64 malware advisory github.com

    OpenSSF GHSA-rvw8-22w3-342v and GHSA-4h5p-w547-9qmv published Nov 2 2026; Leitwacht advisories LWA-2026-13557 and LWA-2026-13564; GitHub advisory GHSA-556m-xfwj-7wff (MAL-2026-18603) for @ifasn/ms-doc-mcp Relevant detection rules: - Monitor access to cloud metadata endpoints (169.254.169.254, 100.100.100.200 (Alibaba), metadata.google.internal, etc.) - Alert on unauthorized reads of /etc/shadow, ~/.ssh/id_rsa, ~/.ssh/id_ed25519, .env files - Detect access to Kubernetes service account tokens (/var/run/secrets/kubernetes.io/) - Monitor HTTP headers for sensitive environment variable leakage (WALLET_PRIVATE_KEY, AWS_SECRET_ACCESS_KEY, etc.) - Alert on npm package installations from unverified sources - Note: Cloud metadata access typically detected via network monitoring or instance-level audit logs (CloudTrail, Azure Monitor, GCP Cloud Logging). File access requires host-based file integrity monitoring.

    Record & downloads
    Source record name
    Malicious MCP servers on npm (ifasn, gadgethumans)
    Entry ID
    malicious-mcp-servers-npm-2026-11
    Catalog review
    November 15, 2026
    AI-role confidence
    high
    Category
    attacks-on-ai
    AI involvement confidence
    confirmed