What does the mlc-ai-nightly-rocm62 malware do?

Installing the package exfiltrates information about the host, including environmental variables. Category: MALICIOUS - The campaign has clearly malicious intent, like infostealers. Campaign: 2025-01-mlc-ai-nightly Reasons (based on the campaign): - The package contains code to exfiltrate basic data from the system, like IP or username. It has a limited risk. - The package overrides the install command in setup.py to execute malicious code during installation. - exfiltration-env-variables - dependency-confusion

Which versions of mlc-ai-nightly-rocm62 are malicious?

The following PyPI versions of mlc-ai-nightly-rocm62 are flagged malicious: 9.9.9. Treat any of these as compromised.

How do I remediate mlc-ai-nightly-rocm62 if I installed it?

mlc-ai-nightly-rocm62 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 mlc-ai-nightly-rocm62 — how do I know if it already compromised me?

If mlc-ai-nightly-rocm62 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.

Is mlc-ai-nightly-rocm62 part of a known attack campaign?

Yes — mlc-ai-nightly-rocm62 is associated with the RLMA-2025-01223, 2025-01-mlc-ai-nightly, RLUA-2026-00527 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 mlc-ai-nightly-rocm62 across my projects, lockfiles, and CI pipelines?

Scan your lockfiles (package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, etc.) and build artifacts for mlc-ai-nightly-rocm62 (version 9.9.9). O3 Security's supply-chain scanner checks every dependency against known-malicious package intelligence at install time and in CI, flagging mlc-ai-nightly-rocm62 across your stack and pipelines.

Malicious package

mlc-ai-nightly-rocm62PyPI

Malicious code in mlc-ai-nightly-rocm62 (PyPI) Remove it immediately and rotate any exposed credentials.

MAL-2025-1982

Immediate action

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

pip uninstall mlc-ai-nightly-rocm62

What this malware does

Installing the package exfiltrates information about the host, including environmental variables.

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

Campaign: 2025-01-mlc-ai-nightly

Reasons (based on the campaign):

The package contains code to exfiltrate basic data from the system, like IP or username. It has a limited risk.
The package overrides the install command in setup.py to execute malicious code during installation.
exfiltration-env-variables
dependency-confusion

Malicious versions

1 flagged

9.9.9

Indicators of compromise (SHA-256)

21e9ff8aa8baa2fa66566f09a96f812b7d158cb7d8570aea4f20a634e630dade

3accdd849420abc9915ec783d6e922f8d855863e4a6092e90648481d1c3fe530

d19b7d0a36e093c723972a96552235036df64fd3c5e2ba6bb85d979a4c65c00d

38c58eadf0180af4d0acfbd88c4e995475f9316a397bc7717f8d5132f1211d8f

f0c638762725a4691aaaa3cf71ce201531a2a054a16e3b4e2d8d02760ec5e2ed

Detection & response playbook

Credential / info stealer

Find it
Scan your lockfiles (package-lock.json, pnpm-lock.yaml, yarn.lock, requirements.txt, poetry.lock, etc.) and build artifacts for mlc-ai-nightly-rocm62 (version 9.9.9). O3 Security's supply-chain scanner checks every dependency against known-malicious package intelligence at install time and in CI, flagging mlc-ai-nightly-rocm62 across your stack and pipelines.
If you installed it — respond
mlc-ai-nightly-rocm62 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 mlc-ai-nightly-rocm62 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 mlc-ai-nightly-rocm62 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

No. mlc-ai-nightly-rocm62 on PyPI has been identified as a malicious package (version 9.9.9 flagged). It should be removed immediately — do not install or keep it in your dependency tree.

Campaign

RLMA-2025-012232025-01-mlc-ai-nightlyRLUA-2026-00527

References

bad-packages.kam193.eu

Credits

Kamil Mańkowski (kam193)
ReversingLabs · finder

Detect & block this

O3 blocks mlc-ai-nightly-rocm62-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