CVE-2026-107287
Pydantic AI: Excessive resource use when local web fetching converts nested HTML
No known exploitation. EPSS puts it in the 19th percentile. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
- Pydantic-aiAffected: >= 1.77.0, < 1.107.7Upgrade to: not statedAffected: >= 2.0.0b1, < 2.52.0Upgrade to: not statedStated by: CVE record
- Pydantic-ai-slimAffected: >= 1.77.0, < 1.107.7Upgrade to: not statedAffected: >= 2.0.0b1, < 2.52.0Upgrade to: not statedStated by: CVE record
Versions as the sources state them. Full version matrix after sign-in
What it is
From the CVE record
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.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
0.3% chance of exploitation activity in the next 30 days, which ranks it in the 19th percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
10 events over 6 days, from the signal feeds we watch.
- Patch availablerecord updated
- Patch availablerecord updated
- Publishedweakness classified, att&ck mapped, record updated, record updated, record updated
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Scored 6.5 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity LowNo special conditions — the attack can be reliably reproduced
- Privileges Required NoneNo authentication required — anyone can exploit this
- User Interaction RequiredA user must click a link, open a file, or perform some action
Scope
- Scope UnchangedImpact is limited to the vulnerable component itself
Impact if exploited
- Confidentiality NoneNo confidentiality impact
- Integrity NoneNo integrity impact
- Availability HighTotal denial of service — the component is completely unavailable
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
Sources
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Pydantic Ai, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI