Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0.
CVE-2026-107287
MEDIUMPre-NVD 6.56.5—Trending — 3 sources updated this week
EchelonGraph scoreMEDIUM confidence
This medium-severity CVE scores 6.5 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.3% (18th percentile of EPSS-scored CVEs). GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).
Triggered by: NVD CVSS baseline
Sources: epss, secondary
6.5EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
- Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.3%CVSS: 6.5Exploit: None knownExposed services: Not assessed
A fix is available — apply it.
- CVSS v3
- 6.5
- EG Score
- 6.5MEDIUMmedium confidence
- EG Risk
- 34EG Risk 34/100CISA SSVC
EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).
How it’s computedSeverity65% × 45%Exploitation0% × 40%Automatability30% × 15%CISA SSVC: Track at low or medium mission impact; Track or Attend at high (mission-essential systems).Action: A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high. - EPSS PROB
- 0.3%
- EPSS %ILE
- 18th
- KEV
- Not listed
CISA SSVCTrack at low or medium mission impact; Track or Attend at high (mission-essential systems).
A fix is available. Apply it within your standard update timelines at low or medium mission impact and sooner than that at high.
Exploitation none (no KEV listing, exploit record or EPSS ≥ 50%) · Automatable unknown (not published for this CVE) · Technical impact partial (CVSS below 9.0). Mission impact is CISA's Mission & Well-being decision point, and only you can judge it: high means the affected system is essential to your organisation's mission, or its compromise could cause irreversible harm to people. CISA's decision table
Published
October 8, 2026
Last Modified
October 8, 2026
Advisory Details (7)
Auto-updated Oct 8, 2026Patch available. Sources: github, github_pr, github_commit, github_release.
github_release Patch Available
v2.52.0 (2026-09-29)
Patch available: pydantic/pydantic-ai v2.52.0
https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0github_release Patch Available
v1.107.7 (2026-09-29)
Patch available: pydantic/pydantic-ai v1.107.7
https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7github_commit Patch Available
commit 2fd38792693d (pydantic/pydantic-ai)
Patch available: pydantic/pydantic-ai v1.107.7 (contains commit 2fd38792693d)
https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545github_commit Patch Available
commit 2b247add4950 (pydantic/pydantic-ai)
Patch available: pydantic/pydantic-ai v2.52.0 (contains commit 2b247add4950)
https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180cgithub_pr Patch Available
Backport bounded `web_fetch` HTML conversion to v1
Patch available: pydantic/pydantic-ai v1.107.7 (PR #8985 merged 2026-09-29)
https://github.com/pydantic/pydantic-ai/pull/8985github_pr Patch Available
Bound HTML conversion cost in `web_fetch`
Patch available: pydantic/pydantic-ai v2.52.0 (PR #8984 merged 2026-09-29)
https://github.com/pydantic/pydantic-ai/pull/8984githubMentions a patch (unverified)
Excessive resource use when local web fetching converts nested HTML · Advisory · pydantic/pydantic-ai · GitHub
https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cwVendor Advisories for CVE-2026-107287(1)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
Affected Packages
(2 across 1 ecosystem)
PyPI(2)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| pydantic-ai | 1.100.0 ... 1.99.0 (42 versions) |
| — |
| pydantic-ai-slim | 1.100.0 ... 1.99.0 (42 versions) |
| — |
Weakness Classification(2)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 5× in last 7d / 5× in last 30d)
Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. 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. Most recent first.
- 2026-10-09 22:03 UTCEG score recompute
- 2026-10-09 20:06 UTCEPSS rescore
- 2026-10-08 16:25 UTCEG score recompute
- 2026-10-08 15:37 UTCEG score recompute
- 2026-10-08 15:36 UTCMITRE cvelistV5first tracked
Related CVEs(same product + same CWE)
Same product
10 shownPyPI:pydantic-ai
Frequently asked(5)
What is CVE-2026-107287?
CVE-2026-107287 is a medium vulnerability published on October 8, 2026. Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local webfetchtool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML…
When was CVE-2026-107287 disclosed?
CVE-2026-107287 was first published on October 8, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-107287 actively exploited?
CVE-2026-107287 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.3% probability of exploitation in the next 30 days (18th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-107287?
CVE-2026-107287 has a CVSS base score of 6.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-107287?
A fix for CVE-2026-107287 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-107287 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-2026-107287
Is Your Infrastructure Affected by CVE-2026-107287?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.