Which versions of openclaw-agent are malicious?

The following PyPI versions of openclaw-agent are flagged malicious: 1.0.3. Treat any of these as compromised.

How do I remediate openclaw-agent if I installed it?

openclaw-agent 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 openclaw-agent — how do I know if it already compromised me?

If openclaw-agent 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 openclaw-agent part of a known attack campaign?

Yes — openclaw-agent is associated with the 2026-05-openclaw-agent 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 openclaw-agent across my projects, lockfiles, and CI pipelines?

Search your lockfiles and build artifacts for openclaw-agent (version 1.0.3).

Malicious package

openclaw-agentPyPI

Advisory published May 20, 2026Updated May 20, 2026

openclaw-agent is a confirmed malicious PyPI package (MAL-2026-4183) that steals credentials and exfiltrates sensitive data (malicious version 1.0.3). Do not install it — remove it immediately and rotate any exposed credentials.

Malicious code in openclaw-agent (PyPI)

MAL-2026-4183

Immediate action

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

pip uninstall openclaw-agent

What this malware does

The package is intended to create a backdoor and steal sensitive data, but the analyzed code did not finally exfiltrate the content of sensitive files.

Category: MALICIOUS - The campaign has clearly malicious intent, like infostealers.

Campaign: 2026-05-openclaw-agent

Reasons (based on the campaign):

exfiltration-generic
impersonation
persistence
peristence-autorun
backdoor
crypto-related
The package overrides the install command in setup.py to execute malicious code during installation.

Malicious versions

1 flagged

1.0.3

Indicators of compromise (SHA-256)

b89b6a94f589218276e6dabe5accf4a6d6a9b22cd7412cce0a58069bccd76bbb

Detection & response playbook

Credential / info stealer

Find it
Search your lockfiles and build artifacts for openclaw-agent (version 1.0.3).
If you installed it — respond
openclaw-agent 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 openclaw-agent 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. openclaw-agent on PyPI has been identified as a malicious package (version 1.0.3 flagged). It should be removed immediately — do not install or keep it in your dependency tree.

Campaign

2026-05-openclaw-agent

References

bad-packages.kam193.eu

Credits

Kamil Mańkowski (kam193) · reporter

Detect & block this

O3 blocks openclaw-agent-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