CVE-2026-114386

Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code

MEDIUM
4.8
CVSS Score
Published: October 21, 2026 at 12:39 PM UTC
Updated: October 22, 2026 at 05:39 PM UTC
1 product affected across 1 vendorpydantic-ai-harness

Using pydantic-ai-harness by pydantic?

Get instant alerts when new vulnerabilities affect pydantic-ai-harness - before attackers find them.

Real-time alertsTrack your software stackFree plan available
Severity
MEDIUM4.8
Exploit prediction
EPSS 0.3%
SSVC
No known exploit

Description

Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools.

Affected

Our own answer: ranges merged, affected separated from platform-only, with confidence and review flags.

All versions

Remediation

No guide yet

No remediation guidance has been written for this CVE yet. What the record does show:

SSVC — Action Prioritization

SSVCNo known exploitNot automatablePartial impact

SSVC signals action urgency (what to patch first), separate from CVSS which measures severity.

CVSS

4.8MEDIUMVulnCheck
Attack Vector
NETWORK
Complexity
HIGH
Privileges
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
LOW
Availability
LOW
Vector?

Quick Info

StatusAWAITING ANALYSIS
CWE
CWE-770

Get alerted

Stop reading CVE feeds looking for your own stack

Track the products you run and VulnTracker tells you when a new CVE affects them — with what is known about fixing it, and nothing about the rest.

Free plan, no card