Lucene search
+L

CVE-2026-114386 Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code

🗓️ 21 Oct 2026 12:39:43Reported by VulnCheckType 
cvelist
 cvelist
🔗 www.cve.org👁 2 Views

Pydantic AI Harness CodeMode toolset fails to enforce tool call limits via run_code.

Related
Affected
Refs
ReporterTitlePublishedViews
Family
circl
Circl
CVE-2026-114386
21 Oct 202617:45
–circl
cve
CVE
CVE-2026-114386
21 Oct 202612:39
–cve
euvd
EUVD
EUVD-2026-107233
21 Oct 202612:39
–euvd
nvd
NVD
CVE-2026-114386
21 Oct 202613:18
–nvd
ptsecurity
Positive Technologies
PT-2026-120573
21 Oct 202600:00
–ptsecurity
vulnrichment
Vulnrichment
CVE-2026-114386 Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code
21 Oct 202612:39
–vulnrichment
[
  {
    "vendor": "pydantic",
    "product": "pydantic-ai-harness",
    "defaultStatus": "unaffected",
    "versions": [
      {
        "version": "0",
        "lessThan": "0.59.0",
        "status": "affected",
        "versionType": "semver"
      }
    ],
    "packageURL": "pkg:pypi/pydantic-ai-harness",
    "repo": "https://github.com/pydantic/pydantic-ai"
  }
]

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation