paperclip-aiPyPI
Advisory published Updated
paperclip-ai is a confirmed malicious PyPI package (MAL-2026-10869) that steals credentials and exfiltrates sensitive data (malicious versions 0.1.0, 0.1.1). Do not install it — remove it immediately and rotate any exposed credentials.
Malicious code in paperclip-ai (PyPI)
What this malware does
No install-time or import-time network I/O, credential access, dropper, silent-relay, or backdoor behavior was identified in this package version. No lifecycle hooks or suspicious build-backend activity were observed.
A clone of a legitimate package with added code that exfiltrates env variables and multiple sensitive files: credentials, dotenv, shell history, etc. Exfiltrated credentials were quickly validated by the attacker.
Category: MALICIOUS - The campaign has clearly malicious intent, like infostealers.
Campaign: 2026-07-browser-use-headless
Reasons (based on the campaign):
-
files-exfiltration
-
exfiltration-env-variables
-
exfiltration-credentials
-
clones-real-package
Malicious versions
Indicators of compromise (SHA-256)
Detection & response playbook
Credential / info stealerFind it
Search your lockfiles and build artifacts for paperclip-ai (2 malicious versions).
If you installed it — respond
paperclip-ai 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 paperclip-ai 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
Campaign
References
Credits
- Amazon Inspector · finder
- Kamil Mańkowski (kam193) · reporter
Detect & block this
O3 blocks paperclip-ai-class packages before install and in CI — and if it already ran, its runtime egress monitoring catches the credential exfiltration and severs the channel.