langchain-core-mcpPyPI
Malicious code in langchain-core-mcp (PyPI) Remove it immediately and rotate any exposed credentials.
What this malware does
Package langchain-core-mcp impersonates the legitimate langchain-core publisher: METADATA sets Project-URL Repository to https://github.com/langchain-ai/langchain and reproduces the upstream README/description verbatim. On install, the package drops two.pth files at the site-packages root — langchain_core-setup.pth (notably using the legitimate package's name) and langchain_core_mcp-setup.pth — both of which Python auto-loads on every interpreter start. The.pth payload is obfuscated into a single line using single-letter aliases (_O, _T, _u, _s, _b, _j, _z,...) and wrapped in exec('...') to evade simple grep-based scanners. When executed, the code creates a sentinel at /tmp/.bun_ran, downloads the Bun runtime ZIP from https://github.com/oven-sh/bun/releases/download/bun-v1.3.13/bun-{platform}-{arch}.zip via urllib.request.urlretrieve to /tmp/b/bun, extracts and chmods +x, then spawns bun run _index.js in the background against the bundled 5.35 MB langchain_core_mcp/_index.js payload. The use of an alien JS runtime (Bun) to execute an opaque bundled payload bypasses Python-only inspection; auto-execution via.pth bypasses pip build isolation and fires on every Python interpreter launch on the installer's machine, not just on import of this package.
Versions 1.4.2, 1.4.3 were compromised.
Compromised packages start an obfuscated infostealer. The infostealer is a heavily obfuscated JavaScript code executed using Bun runtime on Python startup. It collectes all kinds of sensitive data, including API keys, credentials to package repositories, cryptocurrency assets, password manager data. Infostealer actively queries online services to collect additional secrets as well as attempts to gain persistence and spread further by publishing infected packages using collected credentials. Data are exfiltrated likely using Github. The code seems to threaten to wipe the user's data if it detects invalid GitHub tokens. Cleanup should be done with caution.
It seems to be related to the recent Mini Shai Hulud campaign.
Category: MALICIOUS - The campaign has clearly malicious intent, like infostealers.
Campaign: 2026-06-compr-woodpecker
Reasons (based on the campaign):
-
compromised-package
-
exfiltration-env-variables
-
exfiltration-cloud-tokens
-
exfiltration-credentials
-
abuses-pth
-
obfuscation
-
infostealer
-
The package contains code to detect if it is running in a sandbox environment.
-
exfiltration-crypto
-
files-exfiltration
-
destructive-actions
Malicious versions
Indicators of compromise (SHA-256)
Detection & response playbook
Credential / info stealerFind it
Scan your lockfiles (package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, etc.) and build artifacts for langchain-core-mcp (2 malicious versions). O3 Security's supply-chain scanner checks every dependency against known-malicious package intelligence at install time and in CI, flagging langchain-core-mcp across your stack and pipelines.
If you installed it — respond
langchain-core-mcp is built to steal secrets, so assume every credential the build or runtime could read is compromised. Remove it from your project and lockfile, then rotate ALL exposed secrets — npm/registry tokens, cloud keys, CI/CD secrets, SSH keys, and any .env values — from a known-clean machine. Audit logs for unauthorized use of those credentials.
Did it already run?
If langchain-core-mcp was ever installed, its post-install/runtime payload may have already executed. O3's L7 egress monitoring and runtime eBPF sensors detect the credential exfiltration or command-and-control callback after install and block the malicious outbound channel, so you catch and contain the actual compromise — not just the presence of the package.
How O3 protects you
O3 blocks langchain-core-mcp before install through its supply-chain scanner, and if it has already run, detects and severs the exfiltration or C2 callback at runtime through L7 egress monitoring and eBPF.
Frequently asked questions
Campaign
References
Credits
- Amazon Inspector · finder
- Kamil Mańkowski (kam193) · analyst
Detect & block this
O3 blocks langchain-core-mcp-class packages before install and in CI — and if it already ran, its runtime egress monitoring catches the credential exfiltration and severs the channel.