Malicious code in guardrails-ai 0.10.1 (supply chain compromise)
CVE-2026-45758 · GHSA-xmpw-2vmm-p4p6 · published 2026-05-19 · updated 2026-06-09
- Severity
- Critical
- CVSS score
- 9.6
- Chance of exploitation (EPSS)
- 0.28%
- Fixed in
- No fix yet
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
On May 11, 2026 at approximately 6:00 PM Pacific, an attacker published a malicious version of guardrails-ai (0.10.1) to PyPI. Affected: any user who installed guardrails-ai==0.10.1 from PyPI on May 11, 2026. Security researchers identified the malicious package within approximately 2 hours of publication, and PyPI quarantined the repository. Based on our telemetry, we have observed no requests to Guardrails AI infrastructure originating from the malicious 0.10.1 version, and a review of system and access logs has produced no evidence of user data exfiltration through our systems. For the full timeline, technical details, and remediation steps we have taken, see SECURITY_ADVISORY.md.
No fixed release is listed yet for guardrails-ai. Follow the source advisory for updates, and until one ships:
1. Pin to a safe version: guardrails-ai==0.10.0 2. While the PyPI quarantine is active, install from GitHub: pip install git+https://github.com/guardrails-ai/[email protected] The v0.10.0 tag in this repository is clean. Track quarantine status here: #1473. 3. If you installed 0.10.1, treat the host as potentially compromised. …
General guidance from ShieldPi, not a vendor fix
- Compromised release. Move to a release the advisory names as clean, and rotate every credential, token and key the environment that ran the affected release could read.
No patched version above 0.10.1 is available yet. Downgrade to 0.10.0, which is unaffected.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| guardrails-ai | PyPI | = 0.10.1 | No fix yet |
- CriticalMalicious dropper in mistralai 2.4.6 PyPI packagemistralai
- CriticalCompromise of PyTorch Lightning PyPi Package Versionspytorch-lightning, pytorch-lightning
- CriticalTwo LiteLLM versions published containing credential harvesting malwarelitellm
- CriticalMalicious code in guardrails-ai (PyPI)guardrails-ai
- CriticalGuardrails AI contains a code injection vulnerability in its Hub package installation mechanismguardrails-ai
- HighGuardrails has an arbitrary code execution vulnerabilityguardrails-ai
- HighGuardrails AI vulnerable to Improper Restriction of XML External Entity Referenceguardrails-ai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.