Exploitation riskElevated riskHow this is measuredCombines four public sources, each answering a different question. CVSS (NVD) scores how bad exploitation would be. KEV (CISA) confirms exploitation is happening. EPSS (FIRST) estimates the chance of exploitation in the next 30 days. LEV (NIST CSWP 41) compounds a CVE's own EPSS history into the chance it has already been exploited. “Elevated” means EPSS at or above 10%; LEV is counted as material at 10%. LEV and EPSS are statistical estimates about a vulnerability, not findings about this vendor — and LEV is a stated lower bound, so “10%” means “at least 10%”, never “probably happened”. The underlying CVEs are matched to this vendor by name, not by exact product/version, so check each linked NVD record before drawing conclusions.
4 of 4 CVEs assessed
0
confirmed exploited
0
EPSS ≥ 10%
11%
highest single CVE
Likely-exploited estimates here rest on a median of 2 EPSS observations per CVE — too little history to read as a trend yet. It deepens daily as scores are collected.
RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from …
An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML fi…
Guardrails AI thru 0.6.7 contains a code injection vulnerability (CWE-94) in its Hub package installation mechanism. When installing validator packages via guar…
Guardrails AI is a Python framework that helps build AI applications. On May 11, 2026 at approximately 6:00 PM Pacific, an attacker published a malicious versio…
Recent changes
last 90 days
CVE-2024-6961 is now estimated at a 10% chance of having already been exploited, despite not appearing on CISA's Known Exploited Vulnerabilities catalog.2026-09-02 · NVD ↗
CVE severity over timeUI-24 — CVE severity timelineEvery known CVE with a disclosure date and severity, plotted by when it was published — lets you see whether disclosures are trending toward more or less severe, not just a raw count. Same NVD-sourced, name-matched data as the list below.
CVEs by year and severity
Count of matched CVEs by the year NVD published them.
Year
Critical
High
Medium
Low
Unscored
Total
2026
2
0
0
0
0
2
2024
0
1
1
0
0
2
Highest EPSS scores
EPSS is FIRST's estimate of the chance a CVE is exploited in the next 30 days. It measures likelihood, not impact.
Known CVEs (4)About this listSourced from the public NVD database, matched by vendor name. This is a name-based match, not exact version tracking — always check the linked NVD record for affected versions before drawing conclusions. “New” means published within the last 30 days. “Actively exploited” means CISA's Known Exploited Vulnerabilities (KEV) catalog confirms real-world exploitation, not just a theoretical severity score. An “EPSS” chip appears at 10% and above: that is FIRST's estimated chance of exploitation in the next 30 days, which measures likelihood rather than impact and so can differ sharply from the severity beside it. See the Exploitation risk panel above for the full picture.
Guardrails AI is a Python framework that helps build AI applications. On May 11, 2026 at approximately 6:00 PM Pacific, an attacker published a malicious version of `guardrails-ai` (0.10.1) to PyPI. A…
Guardrails AI thru 0.6.7 contains a code injection vulnerability (CWE-94) in its Hub package installation mechanism. When installing validator packages via guardrails hub install, the system retrieves…
CVEs come from the US National Vulnerability Database (NVD) and are matched to Guardrails AI by vendor name. A name match can include CVEs that concern a similarly named product, and can miss ones filed under another name. The count reflects how widely a vendor's software is deployed and examined as much as anything else, so it is not a measure of how secure the vendor is and should not be used to rank vendors. Latest CVE added here: 2026-07-11.
Known-exploited status comes from the CISA Known Exploited Vulnerabilities (KEV) catalog. Last checked: 2026-10-21.
Exploit probability (EPSS) comes from FIRST. Latest score date: 2026-10-20.
CVE-2024-45858
HIGH 7.82024
An arbitrary code execution vulnerability exists in versions 0.2.9 up to 0.5.10 of the Guardrails AI Guardrails framework because of the way it validates XML files. If a victim user loads a maliciousl…
RAIL documents are an XML-based format invented by Guardrails AI to enforce formatting checks on LLM outputs. Guardrails users that consume RAIL documents from external sources are vulnerable to XXE, …
