Which versions of litellm are malicious?

The following PyPI versions of litellm are flagged malicious: 1.82.7, 1.82.8, 1.107.0. Treat any of these as compromised.

How do I remediate litellm if I installed it?

litellm 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.

I already installed litellm — how do I know if it already compromised me?

If litellm was installed, its post-install payload may already have run. Removing the package does not undo that — check outbound connections and credential use from the install window onward.

Is litellm part of a known attack campaign?

Yes — litellm is associated with the IN-MAL-2026-022275 campaign. Packages in the same campaign often share infrastructure and payloads, so check whether any related packages are also in your dependency tree.

How do I find litellm across my projects, lockfiles, and CI pipelines?

Search your lockfiles and build artifacts for litellm (3 malicious versions).

Malicious package

litellmPyPI

Advisory published Mar 24, 2026Updated Oct 29, 2026

litellm is a confirmed malicious PyPI package (MAL-2026-2144) that steals credentials and exfiltrates sensitive data (malicious versions 1.82.7, 1.82.8, 1.107.0). Do not install it — remove it immediately and rotate any exposed credentials.

Malicious code in litellm (PyPI)

MAL-2026-2144

Immediate action

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

pip uninstall litellm

What this malware does

litellm 1.107.0, uploaded to PyPI on 2026-10-21 between 11:39 and 11:40 UTC, contains a credential stealer and a remote code execution backdoor that are not in the upstream source (the v1.107.0 git tag of BerriAI/litellm does not contain them): they were injected at build or upload time. Every wheel ships three extra files under litellm-1.107.0.data/purelib/, which pip installs at the site-packages root, so the payload is triggered at every Python interpreter start, without importing litellm.

cook.pth contains import cook.
cook.py runs exec(zlib.decompress(base64.b64decode(...))), an info stealer (self-named "privcollect") that collects browser passwords and history, SSH keys, shell history, AWS/GCP/Azure credentials and cloud instance metadata (169.254.169.254, 169.254.170.2), Kubernetes, Docker, Vault and CI secrets, AI developer tool configurations (~/.cursor, ~/.claude, ~/.kiro, Windsurf), GPG and TLS private keys, .npmrc, .pypirc, .git-credentials and environment variables, encrypts them with an embedded RSA-4096 key and POSTs them to http://www.litellm.dev/healthcheck. It leaves the marker /tmp/.pc_once_72129118c59f5636c0bb.
sitecustomize.py daemonizes at interpreter start and, every hour, fetches a domain list from https://raw.githubusercontent.com/letters9813/pythonclient-test/main/domain.txt, then downloads and executes code from http://<domain>/codepy (remote shell / dropper).

The same mechanism (a .pth file run at interpreter start) was used in litellm 1.82.7 and 1.82.8 (MAL-2026-2144). Releases 1.106.2 and 1.107.0rc1/rc2 are not affected. Any environment where 1.107.0 was installed should be treated as compromised and its credentials rotated.

litellm 1.107.0 is a Python LLM gateway/proxy library. No install-time or import-time code paths were observed that exfiltrate installer secrets, fetch and execute remote payloads, open a backdoor, redirect the installer's package manager, or distribute live third-party credentials. No lifecycle hooks performing network I/O, no.pth side effects beyond sys.path handling, and no credential-harvesting primitives against installer-owned paths (~/.aws, ~/.ssh, ~/.npmrc, browser or wallet stores) were found in the shipped artifact.

LiteLLM was compromised through trivy security scan in a GitHub workflow. Attackers uploaded malicious versions of LiteLLM to PyPI. The malicious code would exfiltrate sensitive secrets to an attcker controlled domain.

The OpenSSF Package Analysis project identified 'litellm' @ 1.82.8 (pypi) as malicious.

It is considered malicious because:

The package executes one or more commands associated with malicious behavior.

Malicious versions

3 flagged

1.82.71.82.81.107.0

Indicators of compromise (SHA-256)

6a89401cbf53902e8374fbf3b424a77bb5e5f8c437176232eab7c3237d10ecbe

c1d5a2e721c5f8b33b0530ddf98150cadf034a8cd16483e143fc2925b2cfa70c

d588e32a0d0ef4ceb28300723f845056e9ea26b79358479186124cd37c13d394

Detection & response playbook

Credential / info stealer

Find it
Search your lockfiles and build artifacts for litellm (3 malicious versions).
If you installed it — respond
litellm 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 litellm was installed, its post-install payload may already have run. Removing the package does not undo that — check outbound connections and credential use from the install window onward.

Frequently asked questions

No. litellm on PyPI has been identified as a malicious package (versions 1.82.7, 1.82.8, 1.107.0 flagged). It should be removed immediately — do not install or keep it in your dependency tree.

Campaign

IN-MAL-2026-022275

References

Credits

Amazon Inspector · finder
OpenSSF: Package Analysis · finder
Timothe Boulet · reporter

Detect & block this

O3 blocks litellm-class packages before install and in CI — and if it already ran, its runtime egress monitoring catches the credential exfiltration and severs the channel.

Malware detection Runtime egress monitoring

Explore

All malware advisories How O3 detects malware Vulnerability database