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.
CVE-2026-114386
MEDIUMPre-NVD 4.84.8
EchelonGraph scoreHIGH confidence
“—” beside the score: it is equal to the CVSS score beside it.
Score 4.8 from GitHub Security Advisory published 2026-10-21. A secondary CVSS source baseline 4.8; sources differ by 0.0.
Triggered by: GitHub Security Advisory CVSS
Sources: EPSS, GitHub Security Advisory, a secondary CVSS source
Also known asEUVD-2026-107233 (ENISA EUVD) · GHSA-3589-pxp7-3gj8 (GitHub Security Advisories)Source: ENISA EUVD
4.8EG
EchelonGraph verdictMonitorRemediate within your standard update timelines (the SSVC decision on this page).
- Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.3%CVSS: 4.8Exploit: None knownExposed services: Not assessed
A fix is available — apply it.
- CVSS v3
- 4.8
- EG Score
- 4.8MEDIUMhigh confidence
- EG Risk
- 22EG Risk 22/100
EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.
How it’s computed (value × EchelonGraph’s weight)Severity48% × 45%Impact severity (EG Severity): CVSS 4.8 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation0.4% × 40%FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.Automatability0% × 15%CISA's SSVC Automatable value: no (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.Action: A fix is available. Apply it within your standard update timelines. - EPSS PROB
- 0.3%
- EPSS %ILE
- 28th
- KEV
- Not listed
What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)
The EG score (4.8): severity, escalated by confirmed exploitation. This CVE's 4.8 is its impact severity (EG Severity), not escalated.
- EG Severity
- 4.8 MEDIUMCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
- EG Likelihood
- 0.3% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-28). FIRST's exploitation probability, not an EchelonGraph model.
- Confirmed exploitation
- None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
- EG Priority
- SSVC Track at medium mission impactTrack at every mission impact level.CISA BOD 26-04: 60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.
SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.
A fix is available. Apply it within your standard update timelines.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table
BOD 26-04 (CISA's remediation timeline, Table 1)60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.
The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it
Published
October 21, 2026
Last Modified
October 22, 2026
Advisory Details (6)
Auto-updated Oct 22, 2026Patch available. Sources: github_commit, github_pr, github_release.
Web page
Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code | Advisories | VulnCheck
https://www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-call-limit-bypass-via-run-codeGitHub release Patch Available
v2.59.0 (2026-10-20)
Patch available: pydantic/pydantic-ai v2.59.0
https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0GitHub pull request Patch Available
Check `tool_calls_limit` before each `CodeMode` nested tool call
Patch available: pydantic/pydantic-ai v2.59.0 (PR #10362 merged 2026-10-21)
https://github.com/pydantic/pydantic-ai/pull/10362GitHub commit Patch Available
commit eb27b2b89fe7 (pydantic/pydantic-ai)
Patch available: pydantic/pydantic-ai v2.59.0 (contains commit eb27b2b89fe7)
https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949Web page
pydantic-ai/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py at v2.58.0 · pydantic/pydantic-ai · GitHub
https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680Vendor Advisories for CVE-2026-114386(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| pydantic-ai-harness | 0.1.1 ... 0.9.0 (48 versions) |
| — |
Weakness Classification(1)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 8× in last 7d / 22× in last 30d)
Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.
- 2026-11-01 16:33 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-31 16:32 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-30 16:33 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-29 16:32 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-29 15:14 UTCEG score recompute
- 2026-10-28 16:31 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-27 16:31 UTCEPSS rescoreEPSS 0.3% · 28th percentile
- 2026-10-26 16:30 UTCEPSS rescoreEPSS 0.3% · 27th percentile
- 2026-10-25 16:32 UTCEPSS rescoreEPSS 0.3% · 27th percentile
- 2026-10-25 14:50 UTCEG score recompute
- 2026-10-24 16:32 UTCEPSS rescoreEPSS 0.3% · 26th percentile
- 2026-10-23 16:31 UTCEPSS rescoreEPSS 0.3% · 26th percentile
- 2026-10-22 17:50 UTCEG score recompute
- 2026-10-22 17:50 UTCGHSA enrichmentGHSA-3589-pxp7-3gj8 · GitHub CVSS 4.8
- 2026-10-22 16:33 UTCEPSS rescoreEPSS 0.3% · 26th percentile
- 2026-10-21 20:25 UTCEG score recompute
- 2026-10-21 20:25 UTCGHSA enrichmentGHSA-3589-pxp7-3gj8 · GitHub CVSS 4.8
- 2026-10-21 20:02 UTCEG score recompute
- 2026-10-21 20:02 UTCGHSA enrichmentGHSA-3589-pxp7-3gj8 · GitHub CVSS 4.8
- 2026-10-21 14:30 UTCEG score recompute
- 2026-10-21 12:53 UTCMITRE cvelistV5first tracked
- 2026-10-21 12:51 UTCEG score recomputeFirst assessed: 4.8 MEDIUM
Related CVEs(same CWE)
Frequently asked(5)
What is CVE-2026-114386?
CVE-2026-114386 is a medium-severity vulnerability; its CVE record was published on October 21, 2026. 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…
When was CVE-2026-114386 made public?
CVE-2026-114386 was made public on October 15, 2026: that is the date its CVE record's CNA, VulnCheck, gives for when the vulnerability was made public. The CVE record itself was published on October 21, 2026. EchelonGraph's copy of the record carries a last-modified date of October 22, 2026; the record at its source may have been updated since.
Is CVE-2026-114386 actively exploited?
CVE-2026-114386 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.3% probability of exploitation in the next 30 days (28th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-114386?
CVE-2026-114386 has a CVSS base score of 4.8 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-114386?
A fix for CVE-2026-114386 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-114386 are linked in the Vendor Advisories panel on this page.
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-114386
Is Your Infrastructure Affected by CVE-2026-114386?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.