CVE database · Agent frameworks and SDKs
Guardrails AI vulnerabilities and CVEs
The Beam CVE database tracks 4 security advisories for Guardrails AI: 2 critical and 2 high severity. The newest is CVE-2026-45758, published May 19, 2026.
A library for validating LLM inputs and outputs.
Check your version: pip show guardrails-ai
- Vulnerabilities tracked
- 4
- Critical
- 2
- Known exploited (CISA KEV)
- 0
- Published in the last 30 days
- 0
All entries, newest first
CVE-2026-45758
Malicious code in guardrails-ai 0.10.1 (supply chain compromise)
critical9.6No fixMay 19, 2026CVE-2026-31233
Guardrails AI contains a code injection vulnerability in its Hub package installation mechanism
critical9.8No fixMay 12, 2026CVE-2024-45858
Guardrails has an arbitrary code execution vulnerability
high8.8Sep 18, 2024CVE-2024-6961
Guardrails AI vulnerable to Improper Restriction of XML External Entity Reference
high5.9Jul 21, 2024